Server Quality Checklist

Tool Scores

• search_papersA
  4/5.0
  Behavior3/5

  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 covers the sources searched, the type of content returned, and general use case. It omits details like result aggregation across sources, defaults, rate limits, or pagination behavior, but those are not critical for a straightforward read-style search.

  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?

  Two compact sentences deliver scope, return values, and usage without filler. 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.

  Completeness4/5

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

  The description is sufficient for a search tool with no output schema or annotations: it states what is searched, what is returned, and how to use it. Could be stronger by mentioning how results are structured or explicitly routing to fetch_paper, but the core calling context is covered.

  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%, so the baseline is 3. The description echoes the query flexibility already documented in the schema and adds no new meaning for the sources or max_results 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?

  Description states a specific verb ('Search') and resource ('academic papers') across named sources, and enumerates return fields. The 'search' verb clearly distinguishes it from the sibling 'fetch_paper', which implies retrieving a specific paper.

  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?

  Says explicitly 'Use this to find papers by topic, author, or keyword,' giving clear context for when to use it. However, it does not explicitly contrast with fetch_paper or state when not to use this tool, so exclusion guidance is absent.

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

• fetch_paperA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden. It reveals the ordered fallback strategy (arXiv, PubMed Central, Unpaywall) and the output form (extracted text from PDF). It does not describe failure behavior when no open-access source has the paper, but the primary behavior is well 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?

  Two tight sentences with no filler: action and inputs come first, followed by source order and return type. Every sentence earns its place.

  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?

  Core behavior and return type are covered, but with no annotations and no output schema it omits what happens when no ID is supplied, when multiple IDs conflict, or when the full text is unavailable. Since all parameters are optional in the schema, the at-least-one-identifier requirement should be clarified. These are clear but non-fatal gaps.

  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 schema already documents all three identifier parameters with examples. The description adds no additional parameter-level meaning, so baseline score of 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?

  States a specific verb, resource, and input types: fetch full text of a paper using DOI, arXiv ID, or PubMed ID. This clearly distinguishes it from the sibling search_papers tool, which would search rather than retrieve full text.

  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?

  Defines a clear trigger condition: use this when you already have a paper identifier and want the full text. It does not explicitly discuss when to prefer search_papers, but the identifier-based precondition makes the intended context unambiguous.

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