Server Quality Checklist

Tool Scores

• analyze_ai_writingA
  4.1/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true, and the description does not contradict this. It adds valuable behavioral context beyond the annotation: 'Runs fully offline; the text never leaves the machine' and the caveat 'This is a signal, not proof of AI authorship.' It also outlines the return structure, which is helpful given no output schema.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences, each earning its place: first defines the analysis scope, second details the rich output structure, third includes offline privacy and an interpretive caveat. It is front-loaded with the primary action and avoids redundancy, making it highly efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With no output schema, the description thoroughly covers return values (score, verdict, counts, statistics, findings with fixes), languages, offline behavior, and limitations ('signal, not proof'). For a two-parameter tool, this is complete and leaves no significant gaps for an agent to invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description adds minimal parameter meaning beyond the schema: it mentions English & Spanish, aligning with the language parameter, but does not provide additional syntax, defaults, or constraints beyond what the schema already states. The purpose context is helpful but does not materially enrich parameter understanding.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('analyzes'), resource ('text'), and scope ('stylometric tells of AI writing'), enumerating the categories and outputs. It distinguishes itself from siblings by focusing on AI-writing detection and returning a 0-100 score, while sibling tools like 'measure_predictability' and 'check_originality' target different aspects.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use the tool by detailing its capabilities (e.g., analyzing text for AI tells, offline privacy), but it does not explicitly state when to use it versus alternatives or mention any exclusions. Users can infer usage context but receive no direct guidance on selecting this tool over siblings.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• search_catalogA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true, and the description adds the 'Offline' behavioral trait and what the returned entries contain. This supplements, rather than contradicts, the annotation. The bar is lower due to the annotation, and the added context is valuable.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the action ('Searches the catalog'), and every clause adds relevant information (languages, content, filters, offline nature). No redundant or vague wording.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  This is a simple, read-only search tool with no output schema and only optional filters. The description fully covers what the tool does, what results contain, supported filters, and the offline behavior. Nothing critical is missing for a tool of this complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already documents all three parameters with descriptions (keyword, category, language) at 100% coverage. The description repeats some examples ('Lexical, Rhetorical...') but does not add significant new meaning beyond the schema. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: it searches a catalog of AI-writing 'signs' with English/Spanish coverage, and describes what each entry contains (why it reads as AI and how to fix it). It differentiates itself from sibling analysis tools by explicitly calling it a reference/study aid.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context on when to use it ('Useful as a reference / study aid, or to explain a finding in depth'). It implies it is not the primary analysis tool but does not explicitly name alternatives or state when not to use it, so not a full 5.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• check_citationsA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  The annotation readOnlyHint=true is already present, and the description adds substantial beyond-annotation context: it runs fully offline, sends nothing, cannot determine real vs. fake references, and notes that a missing reference is usually a slip rather than dishonesty. This paints a complete behavioral picture and explains the tool's intent and limitations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is longer than average but every sentence earns its place: it front-loads the core function, then lists specific check types, supported styles, offline behavior, limitations, and even advice on handling findings. No fluff or repetition, just dense, useful information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity and the absence of an output schema, the description does well by stating that it returns 'the line of every problem' and explaining the conceptual approach (self-contradiction detection). It lacks an exact return structure, but that is not fully required, and the description covers language, year handling, and offline behavior sufficiently for an agent to gauge whether this tool fits.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already provides 100% coverage for all three parameters, including defaults and descriptions for each. The tool description does not add any new parameter-level semantics, so it rests at the baseline of 3; it neither clarifies nor conflicts with the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description begins with a specific verb and resource: 'Compares a document against its own reference list and reports where the two disagree.' It enumerates concrete checks (malformed DOI, impossible year, duplicates) and explicitly distinguishes itself from sibling tools like check_originality or check_paraphrase by focusing on internal consistency rather than external similarity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description clearly states supported languages and citation styles, and explicitly identifies a key limitation: it cannot verify whether references are real papers, only whether the document contradicts itself. It does not name specific alternative tools, but the 'nothing is sent anywhere' and offline nature help the agent decide when this (vs. a look-up tool) is appropriate.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• check_paraphraseA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Beyond the readOnlyHint and openWorldHint annotations, the description discloses critical behavioral details: it sends both texts to the SignsOfAI server and requires the embedding feature to be enabled. This is significant operational context not captured by annotations, and there is no contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is exactly two sentences: the first states the core purpose, the second covers mechanism, data flow, and requirements. No wasted words; every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Without an output schema, the description covers the tool's purpose, method, external data transmission, and prerequisite. It does not explicitly state what the tool returns (e.g., matched sentences, similarity score), which would be helpful. Overall, it is fairly complete for a two-input analysis tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100% for all three parameters. The description's mention of cosine similarity reinforces the threshold parameter's semantics but does not add new meaning beyond the schema's own description. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool finds reworded copies between two texts (same meaning, different words), including cross-language, and explicitly distinguishes itself from literal copy checks. This gives a specific verb+resource and differentiates it from sibling tools like check_originality.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context for when to use the tool (when a literal copy check is insufficient) and notes a prerequisite (embedding feature enabled). However, it does not explicitly name alternative tools or state when not to use it, though sibling context hints at this.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• inspect_charactersA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Despite the readOnlyHint annotation already signaling a safe read operation, the description goes far beyond by detailing output specifics (codepoint, line, column, clustering), explaining semantic interpretation (clustered vs. spread), and adding context about legitimate sources. It also clearly states the tool's limitations (not proof of authorship), which is critical behavioral context not conveyed by schemas.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is longer than typical but every section earns its place: it explains what the tool does, what it returns, how to interpret results, and important caveats. The main purpose is front-loaded in the first sentence, and the subsequent content is organized logically. Minor redundancy (e.g., 'exactly as it arrived' is repeated in schema) could be trimmed, but overall it is effectively structured.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity and the absence of an output schema, the description is remarkably complete. It covers the tool's scope, return values, interpretation of clustering, language independence, offline capability, and limitation of evidence. There is no gap that would leave an agent unsure about invocation or result interpretation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, with both parameters (text and language) already described adequately in the input schema. The tool description does not add additional parameter-level semantics, staying within the baseline 3 for schema-covered parameters. No extra syntax, format, or edge-case details are provided beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb ('Reports characters') and a precise resource ('text' inspected for non-typing characters), immediately distinguishing it from sibling tools like measure_predictability or check_originality. It lists concrete categories (invisible, Cyrillic impostors, direction controls, hidden tags) and explicitly frames it as a 'checkable fact,' making the tool's unique contribution unmistakable.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context for when to use this tool: detecting deliberately inserted characters by rewriting tools, and it gives explicit interpretive guidance ('NOT proof of dishonesty') and a recommended action ('ask the writer'). However, it does not name sibling alternatives or state when not to use it, which leaves a small gap in usage guidance.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• measure_predictabilityA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations include readOnlyHint and openWorldHint, but the description goes further by explicitly warning that the text is sent to the SignsOfAI server, mentions the configurable endpoint, and clarifies interpretive limitations. This adds substantial behavioral context beyond the annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences, each with a distinct purpose: definition, interpretation caveat, and network warning. It is front-loaded and free of fluff, making every sentence earn its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description covers the core purpose, caveats, and network behavior, which addresses most usage concerns. However, with no output schema, it would be more complete if it explicitly stated the return format (e.g., a numeric perplexity score). This minor gap prevents a perfect score.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has 100% parameter description coverage for text, model, and language, so the description adds no new parameter-level semantics. The baseline of 3 applies because the schema already documents the parameters sufficiently.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the tool's function: measuring perplexity/predictability of phrasing. The verb 'measures' and the resource (language model's predictability) are specific, and the mention of 'unlike the offline tools' helps distinguish it from sibling tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides important usage context: it is a signal, not proof, and it highlights that this tool sends text to a remote server unlike offline tools. However, it does not explicitly state when to prefer this tool over alternatives like check_originality or analyze_ai_writing.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• check_originalityA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  While annotations declare readOnlyHint=true, the description goes beyond this by disclosing specific behavioral traits: case- and accent-insensitive matching, return of overlap percentage and shared passages, fully offline processing, and a non-accusatory stance. These details provide useful context that annotations alone would not convey.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three sentences long, each earning its place: the first defines the action and gives examples, the second details output and sensitivity, and the third clarifies scope and philosophy. There is zero filler and the most important information is front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter tool with no output schema, the description is remarkably complete. It covers purpose, return values (overlap percentage and shared passages), limitations (not internet-indexed, offline), and intended usage context. An agent would have all necessary information to invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has 100% description coverage for the sole 'documents' parameter, so the baseline is 3. The description adds context that the documents are compared against each other, but it does not add specific format or usage details beyond what the schema already states, so it neither improves nor harms parameter understanding.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Compares') and resource ('documents AGAINST EACH OTHER') to clearly define the tool's function. It distinguishes itself from internet-wide plagiarism tools like Turnitin and from sibling tools by emphasizing pairwise document comparison, ensuring no confusion with tools like compare_to_baseline or check_citations.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly states when to use this tool—comparing a closed set of documents against each other—and provides concrete use cases (student submissions, draft vs sources). It also explicitly excludes a major alternative ('NOT a whole-internet index like Turnitin') and notes the tool operates offline, giving clear contextual guidance.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• extract_distinctive_phrasesA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With readOnlyHint provided, the description adds valuable context: it is offline, does not search the web, and returns ready-made search links. This goes beyond the annotation without contradicting it.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three concise sentences, front-loaded with the main action, and the negative clarification is compact. Every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a two-parameter, read-only extraction tool, the description fully covers purpose, output format (search links), and behavioral constraints (offline, no searching). No output schema is needed as the output is described in prose.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with descriptions for text and maxPhrases. The tool description does not add extra parameter semantics, so a baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool 'Extracts' the specific resource 'DIStinctive phrases from a document' and defines what makes them distinctive. It also distinguishes itself from web-searching siblings by explicitly noting it does not search the web.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly states when to use the tool (to get phrases worth checking on the web) and when not to use it (it does NOT search the web itself). The note 'Offline' further clarifies the operating context, preventing misuse.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• write_reportA
  4.6/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Beyond the readOnlyHint annotation, the description discloses that the tool runs FULLY OFFLINE, that the output contains material from the document (privacy caution), and that it reports its own error rates and rules that may fire on human writing. It also explains the threshold-based verdict suppression.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is longer than typical (7 sentences) but every sentence contributes meaningful detail about purpose, contents, limitations, and usage. It is front-loaded with the main purpose and uses clear structure, though it could be slightly tighter without losing value.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description comprehensively covers what the report includes (score, signals, character locations, citation discrepancies), reliability metrics, threshold rules, offline behavior, and privacy considerations. This is especially important because there is no output schema, and the description fully compensates for that.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema provides 100% coverage with clear descriptions for all 5 parameters. The tool description does not add significant meaning beyond what the schema already offers; it references report contents but doesn't elaborate on individual parameter behavior.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool produces a complete Markdown analysis document, distinguishing it from sibling tools that provide individual analyses. It identifies the resource (full analysis report) and the specific verb 'produces', and explicitly contrasts with paraphrasing other tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives explicit usage guidance: 'Prefer this over paraphrasing the other tools' output when the user wants something to send, save, print or attach.' It also mentions that no verdict is given below a reliability threshold, setting expectations for when output may be withheld.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• compare_to_baselineA
  4.7/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Beyond the readOnlyHint annotation, the description discloses rich behavioral details: it runs fully offline, refuses on thin evidence returning 'Undetermined', uses the writer's own variation as the scale, and explicitly forbids interpreting results as a 'different author' conclusion. No contradictions with annotations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Although lengthy, every sentence earns its place. The description is well-structured: definition, limitations, recommended use, and behavioral caveats are clearly separated. The 'WHAT THIS CANNOT DO' section is critical and formatted for emphasis, adding value without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a complex tool with no output schema, the description fully explains expected return values (distances, function-word rates, never-used rates) and handling of insufficient evidence ('Undetermined'). It also covers interpretation and ethical cautions, making it complete for real-world use.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so parameters are fully documented in the input schema. The description adds conceptual context (e.g., 'earlier pieces by the SAME person') but does not add significant new parameter-specific details beyond what the schema already states. Baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Compares one piece of writing against several earlier pieces by the SAME person, using function-word frequencies (Burrows's Delta).' This specifies the verb and resource, and the explicit note that it cannot determine authorship distinguishes it from sibling analysis tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit when-to-use guidance: 'The most valuable outcome is the reassuring one: a text INSIDE the range settles a suspicion.' It also states what it cannot do ('it cannot tell you who wrote something') and advises against workarounds for 'Undetermined' results, giving clear exclusions and alternatives.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.