Server Quality Checklist

Tool Scores

• extract_markdown_advancedA
  4.1/5.0
  Behavior3/5

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

  With no annotations, the description must carry the full burden. It discloses the return type and key parameters, but does not mention access permissions, rate limits, or side effects. Since extraction is inherently read-only, the description is adequate but not rich.

  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 a concise one-sentence summary followed by a structured argument list and return statement. No unnecessary text, and the structure is front-loaded and easy to scan.

  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 all parameters and the return value, which is sufficient for a tool of this complexity. It lacks guidance on choosing this over simpler alternatives, but is otherwise complete for an extraction task.

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

  Parameters5/5

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

  Schema description coverage is 0%, and the description fully compensates by explaining each parameter: file_path (absolute path, PDF/image), pages (1-indexed), table_format_ (markdown/html), model (with default). This adds clear meaning beyond the raw schema types.

  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 'Extract markdown with advanced OCR options', providing a specific verb and resource. The 'advanced' qualifier distinguishes it from the basic 'extract_markdown' sibling tool.

  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 usage for scenarios requiring advanced OCR (model selection, pagination, table formats) but does not explicitly state when to use this tool over alternatives like 'extract_markdown' or 'extract_markdown_from_url'. No exclusions or alternative comparison is provided.

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

• ocr_statusA
  4.3/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the behavioral disclosure burden. It transparently notes that the tool makes a lightweight API call, checks key validity, and returns a status dictionary. It could add more details on error handling or timeouts, but the essentials are covered.

  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 concise and well-structured: the first sentence states the core purpose, followed by a brief behavioral explanation and a clear 'Returns' section. Every sentence provides useful information 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 simple status check tool with no input parameters and an output schema present, the description is fully complete. It covers the tool's purpose, what it does, and what it returns, making it sufficient for an agent to select and invoke correctly.

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

  Parameters4/5

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

  The input schema has zero parameters, so there is nothing to describe beyond the schema. The baseline for zero parameters is 4, and the description appropriately adds no irrelevant parameter details.

  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 with a specific verb and resource: 'Check Mistral API connectivity and key validity.' It also clarifies the action ('Makes a lightweight API call to verify the configured API key is working correctly'), which fully distinguishes it from sibling extraction tools.

  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 this tool (when needing to verify API connectivity/key validity), but it does not explicitly state usage context, exclusions, or alternatives. The sibling tools are contextually different, but no direct comparison is provided.

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

• extract_markdownA
  4.8/5.0
  Behavior5/5

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

  Without annotations, the description thoroughly discloses side effects: saving markdown to disk, saving embedded images, rewriting relative links, and requiring output_dir for include_images. It also documents the conditional return structure, giving the agent full visibility into tool behavior.

  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 docstring is well-organized into a summary, Args, and Returns sections, with no unnecessary filler. Every sentence adds essential information about the tool's behavior and return values.

  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 lack of output schema in view, the description provides a complete account of all possible return values and parameter interactions. It covers both modes (inline vs. file output) and the image handling behavior, leaving minimal ambiguity for the agent.

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

  Parameters5/5

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

  With 0% schema description coverage, the description fully compensates by explaining file_path as an absolute path, output_dir as an existing directory within allowed bounds, and include_images as a dependent flag. This adds significant meaning beyond the bare schema type and defaults.

  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 clear action ('Extract markdown text') and specific source ('PDF or image file'), establishing the tool's purpose. It implicitly distinguishes from sibling tools like extract_markdown_from_url by emphasizing local file paths.

  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?

  Provides clear context for when to use the tool (local PDF or image files) and detailed guidance on parameter combinations (output_dir, include_images). However, it does not explicitly mention when to prefer alternative sibling tools like extract_markdown_from_url or extract_markdown_advanced.

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

• extract_markdown_from_urlA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and it succeeds: it discloses file-saving side effects (output_dir creates a subdirectory with content.md), conditional image handling, the requirement that output_dir exist and be within an allowed directory, and the return value shapes for each mode. This goes well beyond the minimal 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 front-loaded with a clear one-sentence summary, followed by structured Args and Returns sections. Every sentence conveys necessary information, and the formatting makes conditional behavior easy to parse. It is appropriately sized for a tool with three parameters and two operating modes.

  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 tool has moderate complexity with conditional behavior depending on output_dir and include_images. The description fully covers all modes, return types, and disk interactions, making it complete even without an explicit output schema. The return value explanation is sufficiently detailed and aligns with the listed output schema.

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

  Parameters5/5

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

  Schema coverage is 0%, so the description is the sole source of parameter meaning. It provides rich semantics: file_url must be publicly accessible; output_dir must be an existing absolute path within an allowed dir and determines disk-saving path; include_images requires output_dir and triggers image saving plus markdown link rewriting. This fully compensates for the empty schema descriptions.

  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 and resource: 'Extract markdown text from a publicly accessible URL.' It clearly states it processes a PDF or image directly from a URL and contrasts with a local-file flow by saying 'without uploading a local file first,' distinguishing it from sibling extract_markdown.

  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 implies when to use this tool (for URL-based PDFs/images) and explains conditional behaviors for output_dir and include_images. It doesn't explicitly name alternatives or provide 'when not to use' exclusions, but the URL-vs-local context is enough to infer appropriate usage.

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