Server Quality Checklist

Tool Scores

• read_pdfC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention whether the entire PDF is processed, how scanned or image-based PDFs are handled, or what the output format looks like. 'Read' implies non-destructive, but no explicit safety or limitation details are given.

  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 single, front-loaded sentence that clearly states the core function with no unnecessary words. It is efficient and easy to parse.

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

  Completeness2/5

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

  For a tool with siblings and no output schema, the description is too sparse. It does not clarify the scope (full document vs specific pages), mention handling of scanned PDFs, or describe the extracted text format. This could lead to confusion when an agent chooses between read_pdf and read_pages.

  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 for the single file_path parameter, so the description adds no additional parameter meaning beyond what is already documented. A baseline score of 3 is appropriate.

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

  Purpose4/5

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

  The description clearly states the action (read/extract) and resource (PDF file text content), but it does not differentiate from sibling tool read_pages, which also reads text from PDF pages. It is specific and easy to understand.

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

  Usage Guidelines2/5

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

  There is no guidance on when to use this tool versus alternatives like read_pages or search_in_pdf. It simply states the function without any context about exclusions or preferred use cases.

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

• read_pagesB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full burden of behavioral disclosure. It only states the basic operation and does not mention return format, page range validation, error handling, or limitations. This leaves the agent without expected behavior details.

  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 single, concise sentence that front-loads the verb and resource. It contains no unnecessary words or content, making it highly efficient.

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

  Completeness3/5

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

  The tool is simple and the parameter schema is clear, but there are no annotations, no output schema, and no elaboration on behavior or usage. The description covers the basic function but leaves gaps in behavioral context and alternative guidance, making it only minimally complete.

  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 descriptions cover 100% of parameters, so the baseline is 3. The description adds no additional meaning beyond the schema, only referencing 'specific pages' which aligns with start_page and end_page. It does not compensate for any missing parameter context.

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

  Purpose4/5

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

  The description clearly states the action ('Read text content') and the resource ('specific pages of a PDF file'), which gives a precise scope. However, it does not explicitly distinguish itself from sibling tools like read_pdf, though the 'specific pages' qualifier helps infer the differentiation.

  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 the tool is for reading text from selected pages, but it provides no explicit guidance on when to use this tool versus alternatives (e.g., read_pdf for full documents, search_in_pdf for searching). No excluded scenarios or alternative recommendations are mentioned.

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

• search_in_pdfB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the basic action and fails to disclose important behavioral details such as whether the search works with scanned PDFs, what the return value looks like (e.g., page numbers, matches), or how edge cases (e.g., no match) are handled.

  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 single, front-loaded sentence with no filler words. It effectively communicates the core purpose without redundancy, making it highly concise and well-structured.

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

  Completeness2/5

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

  The tool has no output schema and no annotations, so the description should explain return behavior and limitations. It does not mention what the tool returns (e.g., page numbers, boolean, matches) or any constraints like text-based PDFs requirement. For a search tool, this is a significant gap when compared to sibling tools that have clearer outputs.

  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 schema covers all three parameters with meaningful descriptions, so the baseline is 3. The tool description adds no additional parameter information, but since schema coverage is 100%, it does not need to compensate. The description is neutral on parameters.

  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: searching for specific text within a PDF file. It uses a specific verb ('Search') and resource ('PDF file'), and distinguishes itself from siblings like 'read_pdf' and 'read_pages' which focus on reading rather than searching.

  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: use this tool when you need to find text within a PDF. However, it does not explicitly state when not to use it or how it compares to alternatives like 'read_pdf' or 'get_pdf_info'. There is no mention of exclusions or alternative selection.

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

• get_pdf_infoA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It implicitly indicates a read-only operation by focusing on metadata, but does not explicitly state that no content is extracted or that the file is not modified. This is adequate for a simple metadata getter, but lacks explicit safety or return-format details.

  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 single, focused sentence that opens with the verb and resource, mentions the key metadata fields, and contains no redundant information. It is concise and well-structured for the tool's simplicity.

  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?

  For a simple tool with one parameter, full schema coverage, and no output schema, the description adequately conveys the purpose and hints at the return content via examples (title, author, pages). It could explicitly state what is returned, but the examples and clear scope make it reasonably complete.

  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 single parameter file_path has a full schema description, so schema coverage is 100%. The tool description adds no extra meaning beyond what the schema already provides, such as path format or constraints, so it stays at the baseline.

  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 verb 'Get' and the resource 'metadata information from a PDF file', with examples of the metadata returned. It is clearly distinct from sibling tools like read_pdf and read_pages, which handle content extraction, making the purpose unmistakable.

  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 the tool should be used when metadata is needed, but provides no explicit guidance on when to use it versus alternatives. There are no stated exclusions or references to sibling tools, so the usage context is implied rather than explicit.

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