Server Quality Checklist

Tool Scores

• paper_batch_downloadA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden and discloses key behavioral traits: sequential processing, 1-50 max limit, 2s delay, source prioritization (open access before Sci-Hub), and output format (markdown summary). It does not cover error handling or authentication needs, but provides substantial operational context.

  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 core functionality, followed by structured sections for args, returns, and examples. Every sentence earns its place: the first sentence defines purpose and constraints, subsequent sections efficiently document usage 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?

  Given the tool's moderate complexity (batch download with constraints), no annotations, and an output schema present (so return values need not be explained), the description is complete. It covers purpose, usage, parameters, behavior, and examples, providing sufficient context 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.

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It explains both parameters: 'identifiers' as a list of DOIs, arXiv IDs, or URLs, and 'output_dir' as a save directory with default. This adds meaningful semantics beyond the bare schema, though it could detail format constraints for identifiers.

  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 'download' and resource 'multiple papers' with specific scope 'sequentially (1-50 max, 2s delay)'. It distinguishes from sibling tools by specifying batch processing versus paper_download (likely single) and paper_metadata (information retrieval).

  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: for downloading multiple papers (1-50) with a delay. It implies an alternative to paper_download for batch operations but does not explicitly state when-not-to-use or compare with paper_metadata. The prioritization of sources offers some guidance on behavior.

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

• paper_downloadA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it specifies the prioritization of sources (open access first, Sci-Hub as last resort), the return format (Markdown with file path, metadata, source, or error), and includes examples. It does not mention rate limits or authentication needs, but covers the core behavior adequately.

  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 appropriately sized and front-loaded: the first sentence states the purpose, followed by prioritized sources, args, returns, and examples. Each section adds value without redundancy, and the structure is clear and 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?

  Given the complexity (2 parameters, no annotations, but with output schema), the description is complete enough. It explains the tool's purpose, usage, behavior, parameters, and return values, and the output schema likely covers return details, so no gaps remain for effective agent use.

  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?

  Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics: 'identifier' is explained as 'DOI, arXiv ID, or URL' with examples, and 'output_dir' is described as 'Save directory (default: './downloads')'. This clarifies beyond the schema's basic types, though it could detail format constraints (e.g., URL patterns).

  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 specific action ('Download academic paper') and the resources involved ('by DOI, arXiv ID, or URL'). It distinguishes from sibling tools like 'paper_batch_download' (which handles multiple papers) and 'paper_metadata' (which retrieves metadata only) by focusing on single-paper downloading with file output.

  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 this tool (for downloading papers via identifiers) and mentions prioritization of open access sources, which guides usage. However, it does not explicitly state when not to use it or directly compare to alternatives like 'paper_batch_download' for multiple papers, though the distinction is implied.

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

• paper_metadataA
  4.6/5.0
  Behavior4/5

  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 effectively describes key traits: the operation is read-only (implied by 'Get'), performance characteristics ('fast, <1s'), data sources ('Unpaywall, Crossref, arXiv APIs'), and what information is returned. It doesn't mention error handling or rate limits, but covers most essential aspects.

  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 perfectly structured and front-loaded: the first sentence states the core purpose, followed by sources, returns, args, and examples. Every sentence earns its place with no wasted words, making it easy for an agent to parse quickly.

  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 moderate complexity, no annotations, and the presence of an output schema, the description provides excellent completeness. It covers purpose, usage context, behavioral traits, parameter semantics with examples, and mentions the return format. The output schema will handle return value details, so the description doesn't need to duplicate that information.

  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?

  The input schema has 0% description coverage, so the description must fully compensate. It clearly explains the 'identifier' parameter with specific examples of valid formats (DOI, arXiv ID, URL) and provides concrete usage examples, adding substantial value beyond the bare 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 clearly states the tool's purpose with a specific verb ('Get') and resource ('paper metadata'), and distinguishes it from sibling tools by emphasizing it's 'without downloading' (unlike 'paper_download' and 'paper_batch_download'). The phrase 'fast, <1s' adds useful context about performance.

  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 ('without downloading') and implicitly contrasts with download-focused siblings. However, it doesn't explicitly state when NOT to use it or name specific alternatives, which prevents a perfect score.

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