eDiscovery Decoder News/Calc
Free educational MCP for read-only eDiscovery news and TAR/review calculators.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~5,704token 数（工具定义）
~3.4 KB典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 4.46%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"mcp": {
"url": "https://mcp.ediscoverydecoder.com/mcp"
}
}
}远程端点
https://mcp.ediscoverydecoder.com/mcpstreamable-http它能做什么
工具清单
工具（15）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢ping
Health check: confirm the eDiscovery Decoder News/Calc MCP server is reachable before a demo or when troubleshooting a connection. Returns server name and version. No inputs.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"ok": {
"type": "boolean"
},
"server": {
"type": "string"
},
"version": {
"type": "string"
}
},
"required": [
"ok",
"server",
"version"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_capabilities
List the full eDiscovery Decoder MCP surface — every tool, prompt, and resource, plus the suggested demo flow and safety boundaries — with an example prompt for each. Call this first when you are unsure which tool fits the user's question, or when tool-search shows only a partial list.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"server": {
"type": "string"
},
"version": {
"type": "string"
},
"purpose": {
"type": "string"
},
"endpoint": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"purpose": {
"type": "string"
},
"example_prompt": {
"type": "string"
}
},
"required": [
"name",
"purpose",
"example_prompt"
],
"additionalProperties": false
}
},
"prompts": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"purpose": {
"type": "string"
}
},
"required": [
"name",
"purpose"
],
"additionalProperties": false
}
},
"resources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"uri": {
"type": "string"
},
"purpose": {
"type": "string"
}
},
"required": [
"uri",
"purpose"
],
"additionalProperties": false
}
},
"demo_flow": {
"type": "array",
"items": {
"type": "string"
}
},
"safety_boundaries": {
"type": "array",
"items": {
"type": "string"
}
},
"claude_note": {
"type": "string"
}
},
"required": [
"server",
"version",
"purpose",
"endpoint",
"tools",
"prompts",
"resources",
"demo_flow",
"safety_boundaries",
"claude_note"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_demo_guide
Return a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts. Use to give someone a guided demo. For the full machine-readable capability catalog, use list_capabilities instead.
输入模式
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"endpoint": {
"type": "string"
},
"purpose": {
"type": "string"
},
"tools": {
"type": "array",
"items": {
"type": "string"
}
},
"prompts": {
"type": "array",
"items": {
"type": "string"
}
},
"resources": {
"type": "array",
"items": {
"type": "string"
}
},
"suggested_test_prompts": {
"type": "array",
"items": {
"type": "string"
}
},
"safety_boundaries": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"title",
"endpoint",
"purpose",
"tools",
"prompts",
"resources",
"suggested_test_prompts",
"safety_boundaries"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_resource_content(uri)
Fetch the JSON behind a supported edd:// resource — the demo guide, TAR learning path, glossary, or news (latest / brief / by-date). Use when you want resource content but the client cannot read MCP resources directly, e.g. to pull glossary definitions or the news brief as a normal tool result.
输入模式
{
"type": "object",
"properties": {
"uri": {
"type": "string",
"pattern": "^edd:\\/\\/(?:mcp\\/demo-guide|resources\\/tar-learning-path|glossary\\/core|news\\/latest|news\\/brief|news\\/\\d{4}-\\d{2}-\\d{2})$"
}
},
"required": [
"uri"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"uri": {
"type": "string"
},
"mimeType": {
"type": "string"
},
"text": {
"type": "string"
},
"payload": {
"type": "object",
"additionalProperties": {}
}
},
"required": [
"uri",
"mimeType",
"text",
"payload"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_prompt_template(prompt_name, audience, matter_description, week_start)
Return the rendered text of one of this server's guided prompts (mcp-demo-tour, tar-matter-kickoff, weekly-digest). Use when the client can call tools but cannot open MCP prompts directly, or when you want to inspect a prompt's wording before using it.
输入模式
{
"type": "object",
"properties": {
"prompt_name": {
"type": "string",
"enum": [
"mcp-demo-tour",
"tar-matter-kickoff",
"weekly-digest"
]
},
"audience": {
"type": "string",
"minLength": 1
},
"matter_description": {
"type": "string",
"minLength": 1
},
"week_start": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"required": [
"prompt_name"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"arguments": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"template_text": {
"type": "string"
},
"messages": {
"type": "array",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"enum": [
"user",
"assistant"
]
},
"content": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text"
},
"text": {
"type": "string"
}
},
"required": [
"type",
"text"
],
"additionalProperties": false
}
},
"required": [
"role",
"content"
],
"additionalProperties": false
}
}
},
"required": [
"name",
"arguments",
"template_text",
"messages"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_news(query, tags, date_from, date_to, limit)
Find recent eDiscovery / legal-AI / TAR news by topic, tag, or date range. Use when the user asks what's new or recent in eDiscovery, wants stories on a subject, or asks about a time window. For a ready-made top-stories roundup instead, use get_news_brief.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1
},
"tags": {
"type": "array",
"items": {
"type": "string",
"minLength": 1
}
},
"date_from": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"date_to": {
"$ref": "#/properties/date_from"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"source_url": {
"type": "string"
},
"published_at": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"title",
"summary",
"source_url",
"published_at",
"tags"
],
"additionalProperties": false
}
}
},
"required": [
"items"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_news_brief(current_limit, week_limit)
Get the current eDiscovery Decoder news brief: top stories plus a Week in Review breakdown, returned both as structured data and as display-ready Markdown (formatted_brief) with a 'why it matters' line per story. Use when the user wants a roundup or summary of current eDiscovery AI news rather than a keyword search.
输入模式
{
"type": "object",
"properties": {
"current_limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 7
},
"week_limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 3
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"generated_at": {
"type": "string"
},
"source_url": {
"type": "string"
},
"formatted_brief": {
"type": "string"
},
"story_bullets": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"source_url": {
"type": "string"
},
"published_at": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"why_it_matters": {
"type": "string"
}
},
"required": [
"id",
"title",
"summary",
"source_url",
"published_at",
"tags",
"why_it_matters"
],
"additionalProperties": false
}
},
"top_stories": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"summary": {
"type": "string"
},
"source_url": {
"type": "string"
},
"published_at": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"title",
"summary",
"source_url",
"published_at",
"tags"
],
"additionalProperties": false
}
},
"week_so_far": {
"type": "object",
"properties": {
"generated_at": {
"type": "string"
},
"source_url": {
"type": "string"
},
"items": {
"type": "array",
"items": {
"$ref": "#/properties/top_stories/items"
}
},
"breakdowns": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"$ref": "#/properties/top_stories/items/properties/id"
},
"title": {
"$ref": "#/properties/top_stories/items/properties/title"
},
"summary": {
"$ref": "#/properties/top_stories/items/properties/summary"
},
"source_url": {
"$ref": "#/properties/top_stories/items/properties/source_url"
},
"published_at": {
"$ref": "#/properties/top_stories/items/properties/published_at"
},
"tags": {
"$ref": "#/properties/top_stories/items/properties/tags"
},
"why_it_matters": {
"type": "string"
},
"reasons": {
"type": "array",
"items": {
"type": "string"
}
},
"score": {
"type": "number"
},
"score_breakdown": {
"type": "object",
"additionalProperties": {
"type": "number"
}
}
},
"required": [
"id",
"title",
"summary",
"source_url",
"published_at",
"tags"
],
"additionalProperties": false
}
}
},
"required": [
"generated_at",
"source_url",
"items",
"breakdowns"
],
"additionalProperties": false
}
},
"required": [
"generated_at",
"source_url",
"formatted_brief",
"story_bullets",
"top_stories",
"week_so_far"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_review_metrics(true_positives, false_positives, false_negatives, true_negatives)
Score a coded sample when you have a full confusion matrix (true/false positives and negatives) — e.g. comparing a TAR model's calls against a reviewer's. Returns recall, precision, F1, accuracy, and in-sample elusion. Use calculate_control_set_recall if you only have relevant-found vs relevant-missed; calculate_elusion for a discard/null-set sample. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"true_positives": {
"type": "integer",
"minimum": 0
},
"false_positives": {
"type": "integer",
"minimum": 0
},
"false_negatives": {
"type": "integer",
"minimum": 0
},
"true_negatives": {
"type": "integer",
"minimum": 0
}
},
"required": [
"true_positives",
"false_positives",
"false_negatives",
"true_negatives"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"recall": {
"type": "object",
"properties": {
"value": {
"type": [
"number",
"null"
]
},
"formula": {
"type": "string"
},
"note": {
"type": "string"
}
},
"required": [
"value",
"formula"
],
"additionalProperties": false
},
"precision": {
"$ref": "#/properties/recall"
},
"f1": {
"$ref": "#/properties/recall"
},
"accuracy": {
"$ref": "#/properties/recall"
},
"elusion_in_sample": {
"$ref": "#/properties/recall"
}
},
"required": [
"recall",
"precision",
"f1",
"accuracy",
"elusion_in_sample"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_elusion(relevant_found_in_sample, sample_size, confidence_level)
Estimate how much responsive/relevant material may remain in a set you chose NOT to review (the discard, null, or 'elusion' set). Use when a random sample of that excluded set has been coded — e.g. 'we sampled 400 culled docs and found 2 relevant.' Returns the elusion rate and a Wilson confidence interval. For an overall recall % from the same sample, use calculate_tar_recall_estimate. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"relevant_found_in_sample": {
"type": "integer",
"minimum": 0
},
"sample_size": {
"type": "integer",
"exclusiveMinimum": 0
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
}
},
"required": [
"relevant_found_in_sample",
"sample_size"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"elusion_rate": {
"type": "number"
},
"confidence_interval": {
"type": "object",
"properties": {
"lower": {
"type": "number"
},
"upper": {
"type": "number"
},
"method": {
"type": "string",
"const": "wilson"
}
},
"required": [
"lower",
"upper",
"method"
],
"additionalProperties": false
},
"formula": {
"type": "string"
},
"assumptions": {
"type": "object",
"properties": {
"relevant_found_in_sample": {
"type": "number"
},
"sample_size": {
"type": "number"
},
"confidence_level": {
"type": "number"
},
"z_score": {
"type": "number"
}
},
"required": [
"relevant_found_in_sample",
"sample_size",
"confidence_level",
"z_score"
],
"additionalProperties": false
}
},
"required": [
"elusion_rate",
"confidence_interval",
"formula",
"assumptions"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_sample_size(population_size, confidence_level, margin_of_error, estimated_prevalence)
Work out how many documents to randomly sample to estimate a proportion (e.g. richness or elusion) at a target confidence level and margin of error, with finite-population correction. Use when planning a sample before review — 'how big a sample do we need?' Aggregate inputs only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"population_size": {
"type": "integer",
"exclusiveMinimum": 0
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
},
"margin_of_error": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1
},
"estimated_prevalence": {
"type": "number",
"minimum": 0,
"maximum": 1,
"default": 0.5
}
},
"required": [
"population_size",
"margin_of_error"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"recommended_sample_size": {
"type": "integer",
"minimum": 0
},
"raw_sample_size": {
"type": "number",
"minimum": 0
},
"assumptions": {
"type": "object",
"properties": {
"population_size": {
"type": "number"
},
"confidence_level": {
"type": "number"
},
"margin_of_error": {
"type": "number"
},
"estimated_prevalence": {
"type": "number"
},
"z_score": {
"type": "number"
}
},
"required": [
"population_size",
"confidence_level",
"margin_of_error",
"estimated_prevalence",
"z_score"
],
"additionalProperties": false
},
"formula": {
"type": "string"
}
},
"required": [
"recommended_sample_size",
"raw_sample_size",
"assumptions",
"formula"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_tar_recall_estimate(responsive_found, excluded_population_size, elusion_responsive_hits, elusion_sample_size, confidence_level)
Estimate overall TAR recall and how many responsive docs were missed, by combining the responsive count already found with an elusion sample of the excluded set. Use when the user wants a recall % for the whole workflow, not just the elusion rate. For only the elusion rate and its interval, use calculate_elusion. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"responsive_found": {
"type": "integer",
"minimum": 0
},
"excluded_population_size": {
"type": "integer",
"minimum": 0
},
"elusion_responsive_hits": {
"type": "integer",
"minimum": 0
},
"elusion_sample_size": {
"type": "integer",
"exclusiveMinimum": 0
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
}
},
"required": [
"responsive_found",
"excluded_population_size",
"elusion_responsive_hits",
"elusion_sample_size"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"responsiveFound": {
"type": "integer",
"minimum": 0
},
"excludedPopulationSize": {
"type": "integer",
"minimum": 0
},
"elusion": {
"type": "object",
"properties": {
"sampleSize": {
"type": "integer",
"minimum": 0
},
"responsiveHits": {
"type": "integer",
"minimum": 0
},
"pointEstimate": {
"type": [
"number",
"null"
]
},
"confidenceInterval": {
"type": "object",
"properties": {
"lower": {
"type": [
"number",
"null"
]
},
"upper": {
"type": [
"number",
"null"
]
},
"method": {
"type": "string",
"const": "wilson"
}
},
"required": [
"lower",
"upper",
"method"
],
"additionalProperties": false
},
"estimatedMissed": {
"type": [
"number",
"null"
]
},
"estimatedMissedLower": {
"type": [
"number",
"null"
]
},
"estimatedMissedUpper": {
"type": [
"number",
"null"
]
},
"confidenceLevel": {
"type": "number"
}
},
"required": [
"sampleSize",
"responsiveHits",
"pointEstimate",
"confidenceInterval",
"estimatedMissed",
"estimatedMissedLower",
"estimatedMissedUpper",
"confidenceLevel"
],
"additionalProperties": false
},
"estimatedRecall": {
"anyOf": [
{
"type": "object",
"properties": {
"estimate": {
"type": "number"
},
"lower": {
"type": "number"
},
"upper": {
"type": "number"
}
},
"required": [
"estimate",
"lower",
"upper"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"formula": {
"type": "string"
},
"assumptions": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"responsiveFound",
"excludedPopulationSize",
"elusion",
"estimatedRecall",
"formula",
"assumptions"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_prevalence_richness(positive_hits, sample_size, population_size, confidence_level)
Estimate how rich or prevalent a population is — the share that is responsive/relevant/positive — from positive hits in a random sample, with a Wilson confidence interval. Use for 'what % of this set is relevant?' or to size review scope and cost expectations. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"positive_hits": {
"type": "integer",
"minimum": 0
},
"sample_size": {
"type": "integer",
"exclusiveMinimum": 0
},
"population_size": {
"type": "integer",
"exclusiveMinimum": 0
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
}
},
"required": [
"positive_hits",
"sample_size"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"sampleSize": {
"type": "integer",
"minimum": 0
},
"positiveHits": {
"type": "integer",
"minimum": 0
},
"pointEstimate": {
"type": "number"
},
"confidenceInterval": {
"type": "object",
"properties": {
"lower": {
"type": "number"
},
"upper": {
"type": "number"
},
"method": {
"type": "string",
"const": "wilson"
}
},
"required": [
"lower",
"upper",
"method"
],
"additionalProperties": false
},
"confidenceLevel": {
"type": "number"
},
"estimatedPositiveCount": {
"type": [
"number",
"null"
]
},
"estimatedPositiveLower": {
"type": [
"number",
"null"
]
},
"estimatedPositiveUpper": {
"type": [
"number",
"null"
]
},
"formula": {
"type": "string"
}
},
"required": [
"sampleSize",
"positiveHits",
"pointEstimate",
"confidenceInterval",
"confidenceLevel",
"estimatedPositiveCount",
"estimatedPositiveLower",
"estimatedPositiveUpper",
"formula"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢calculate_control_set_recall(relevant_found, relevant_missed, confidence_level)
Calculate recall against a known control set: the share of documents already confirmed relevant that the workflow found, with a Wilson confidence interval. Use when you have relevant-found and relevant-missed counts from a fixed reference set. For recall from a confusion matrix use calculate_review_metrics; from a discard-set sample use calculate_tar_recall_estimate. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"relevant_found": {
"type": "integer",
"minimum": 0
},
"relevant_missed": {
"type": "integer",
"minimum": 0
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
}
},
"required": [
"relevant_found",
"relevant_missed"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"relevantFound": {
"type": "integer",
"minimum": 0
},
"relevantMissed": {
"type": "integer",
"minimum": 0
},
"totalRelevant": {
"type": "integer",
"minimum": 0
},
"recall": {
"type": [
"number",
"null"
]
},
"confidenceInterval": {
"type": "object",
"properties": {
"lower": {
"type": [
"number",
"null"
]
},
"upper": {
"type": [
"number",
"null"
]
},
"method": {
"type": "string",
"const": "wilson"
}
},
"required": [
"lower",
"upper",
"method"
],
"additionalProperties": false
},
"confidenceLevel": {
"type": "number"
},
"formula": {
"type": "string"
}
},
"required": [
"relevantFound",
"relevantMissed",
"totalRelevant",
"recall",
"confidenceInterval",
"confidenceLevel",
"formula"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢compare_tar_cutoffs(scored_document_count, cutoffs)
Compare candidate TAR score or rank cutoffs side by side: for each cutoff, how many docs sit above it, its share of the scored set, and (if responsive counts are given) an estimated precision. Use when deciding where to draw the review/cull line. Aggregate counts only; not legal advice.
输入模式
{
"type": "object",
"properties": {
"scored_document_count": {
"type": "integer",
"exclusiveMinimum": 0
},
"cutoffs": {
"type": "array",
"items": {
"type": "object",
"properties": {
"label": {
"type": "string",
"minLength": 1
},
"cutoff": {
"type": "number"
},
"document_count": {
"type": "integer",
"minimum": 0
},
"responsive_count": {
"type": "integer",
"minimum": 0
}
},
"required": [
"cutoff",
"document_count"
],
"additionalProperties": false
},
"minItems": 1
}
},
"required": [
"scored_document_count",
"cutoffs"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"scoredDocumentCount": {
"type": "integer",
"exclusiveMinimum": 0
},
"cutoffs": {
"type": "array",
"items": {
"type": "object",
"properties": {
"label": {
"type": "string"
},
"cutoff": {
"type": "number"
},
"documentCount": {
"type": "integer",
"minimum": 0
},
"shareOfScored": {
"type": "number"
},
"responsiveCount": {
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
]
},
"precisionEstimate": {
"type": [
"number",
"null"
]
}
},
"required": [
"label",
"cutoff",
"documentCount",
"shareOfScored",
"responsiveCount",
"precisionEstimate"
],
"additionalProperties": false
}
},
"questions": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"scoredDocumentCount",
"cutoffs",
"questions"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢validate_sample_design(population_size, sample_size, confidence_level, margin_of_error, sampling_frame, ...)
QC a TAR validation sampling plan: check whether it has the documented elements needed for a defensibility discussion (population, sample size, confidence level, sampling frame/method, randomization, etc.) and flag what is missing or inconsistent. Use to sanity-check a sampling protocol before relying on it. Reviews metadata only — not a legal sufficiency opinion.
输入模式
{
"type": "object",
"properties": {
"population_size": {
"type": "integer"
},
"sample_size": {
"type": "integer"
},
"confidence_level": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1,
"default": 0.95
},
"margin_of_error": {
"type": "number",
"exclusiveMinimum": 0,
"exclusiveMaximum": 1
},
"sampling_frame": {
"type": "string",
"minLength": 1
},
"sampling_method": {
"type": "string",
"minLength": 1
},
"random_seed": {
"type": "string",
"minLength": 1
},
"generated_at": {
"type": "string",
"minLength": 1
},
"excluded_population_size": {
"type": "integer"
}
},
"required": [
"population_size",
"sample_size"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}输出模式
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"ready",
"needs_attention",
"blocked"
]
},
"issues": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"severity": {
"type": "string",
"enum": [
"info",
"warning",
"critical"
]
},
"detail": {
"type": "string"
}
},
"required": [
"id",
"title",
"severity",
"detail"
],
"additionalProperties": false
}
},
"summary": {
"type": "object",
"properties": {
"populationSize": {
"type": "integer"
},
"sampleSize": {
"type": "integer"
},
"samplingRate": {
"type": [
"number",
"null"
]
},
"confidenceLevel": {
"type": "number"
},
"marginOfError": {
"type": [
"number",
"null"
]
}
},
"required": [
"populationSize",
"sampleSize",
"samplingRate",
"confidenceLevel",
"marginOfError"
],
"additionalProperties": false
}
},
"required": [
"status",
"issues",
"summary"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社区
证据
最近观测
已验证未记录版本15 个工具
已验证未记录版本15 个工具