Server Quality Checklist

Tool Scores

• pubmed_find_relatedA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, covering the safety and repeatability profile. The description adds the relationships explored (similar/reviews) and the intended purpose, but does not disclose return format, ordering, or external call behavior beyond what annotations provide.

  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 with no filler. The core action is front-loaded, and the usage guidance follows immediately. Every sentence contributes meaningful information without redundancy.

  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 read-only lookup tool with fully documented annotations and schema, the description provides adequate context for invocation and purpose. The absence of an output schema means a brief note about return format would be useful, but the tool's relative simplicity makes this a minor gap rather than a critical omission.

  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 schema already documents all three parameters, their defaults, and the enum for 'type'. The description adds no additional parameter-specific detail beyond what is already in the schema, matching the baseline of 3.

  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 states the specific verb 'Find' and a clear resource: articles related to a given PubMed article. It further clarifies the two relationship types (similar papers or review articles) and positions it as distinct from a general search by requiring an existing key paper as input.

  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 explicitly says to use this tool after identifying a key paper to expand the search in relevant directions, giving clear workflow context for when it should be invoked. It does not explicitly name the alternative (e.g., pubmed_search for initial keyword queries), so it falls short of an explicit exclusion or alternative routing.

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

• pubmed_searchA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare the tool as read-only, idempotent, and open-world, and the description aligns with those. It adds useful behavioral context by describing the returned content (metadata, abstracts, citations), supported query syntax, and format-based output options, going beyond the 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 concise and well front-loaded, starting with a direct statement of purpose. Every sentence contributes useful information without redundancy or filler.

  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 6-parameter tool with no output schema, the description covers the core search behavior, return content, query syntax, and format selection. It does not describe pagination or sort behavior in prose, but those are fully documented in the schema, so the overall context is sufficiently complete.

  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 coverage is 100%, so the baseline is 3. The description adds value by explaining Boolean operators, MeSH terms, field tags like [Title] and [Author], and recommending when to use compact versus detailed formats, which supplements the schema descriptions.

  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 tool searches the PubMed biomedical literature database and returns matching articles with metadata, abstracts, and citations. It identifies a specific resource and action, but does not explicitly differentiate itself from sibling tools such as pubmed_find_related or pubmed_get_details.

  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 gives concrete usage context, such as using compact format for quick browsing and detailed for in-depth analysis, and using days_back for recent publications. It does not explicitly mention when to avoid this tool or prefer a sibling, but the usage guidance is clear enough for common search workflows.

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

• pubmed_extract_infoA
  4.2/5.0
  Behavior3/5

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

  The annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered and the description does not need to repeat it. The description adds the token-efficiency observation and the scoping of sections, but does not disclose any deeper behavioral details such as output shape, error behavior, or section-level edge cases. This 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?

  Three sentences with no filler: the purpose is front-loaded, the usage condition follows immediately, and the efficiency advantage is stated once. Every sentence contributes a distinct piece of guidance.

  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 tool has only two parameters, the schema covers both fully, and the annotations cover read-only and idempotent behavior. The description is sufficient for deciding when to call it. It falls slightly short of 5 because there is no output schema and the description does not describe the exact structure or format of the extracted sections, which would be useful for this kind of extraction 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?

  The input schema has 100% coverage, with clear descriptions for 'pmid' and enumerated 'sections'. The description mentions examples of sections ('author details, structured abstract, keywords, DOI) that overlap with those enum values, but adds little meaning beyond what the schema already provides. 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 uses a specific verb ('Extract') with a clear resource ('specific structured sections from a PubMed article') and a concrete scope ('only certain aspects...rather than the full record'). It also differentiates from pubmed_get_details by naming the token-efficiency angle, so an agent can distinguish it immediately.

  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 says to use this tool 'when you need only certain aspects' and contrasts it with 'the full record'. It also names the alternative tool, pubmed_get_details, and the condition under which this one is preferable ('targeted extraction'), giving an agent actionable selection criteria.

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

• pubmed_get_detailsA
  4.2/5.0
  Behavior4/5

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

  The description adds behavioral detail beyond the readOnlyHint, idempotentHint, and openWorldHint annotations: it accepts a single PMID or an array up to 20, and returns fields such as abstract, authors, journal, DOI, and MeSH terms. It does not cover error behavior or rate limits, but annotations already establish the safety profile.

  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 sentences with no filler. The main purpose and input mode are front-loaded, the return content is summarized efficiently, and the usage condition completes the guidance without redundancy.

  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 straightforward read-only lookup tool, the description covers input shape, batch limit, return content, and when to use it. The only notable gap is that the 'format' enum semantics are not described, leaving the agent to infer what 'concise' versus 'detailed' means.

  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 restates the PMID input forms and adds useful output context, but it does not explain the 'format' parameter values (concise, standard, detailed) beyond the schema's minimal 'Output format' label.

  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 and resource: 'Retrieve complete metadata for specific PubMed articles by PMID.' It clearly distinguishes this tool from pubmed_search, pubmed_find_related, and pubmed_extract_info by emphasizing PMID-based retrieval of full records.

  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 explicitly states when to use it: 'Use when you have specific PMIDs from a previous search or citation and need the full record.' It provides clear context but does not explicitly name alternatives or state when not to use it.

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

• pubmed_manage_cacheA
  4.3/5.0
  Behavior4/5

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

  The annotations already flag destructiveHint=true, and the description adds meaningful nuance by specifying that 'clean' removes expired entries while 'clear' wipes a cache layer, and 'stats' is a read-only operation. This helps the agent understand the varying destructiveness of each action beyond the single annotation flag.

  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 compact, front-loaded with the core purpose, and uses a clean pattern of action-to-purpose mapping. Every sentence contributes necessary operational guidance with no filler or 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 two-parameter tool with enum-restricted values and a clear maintenance scope, the description covers the available actions, their effects, and the target layer concept. There is no output schema, but the described behavior is sufficient for an agent to select and 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 already provides full documentation for both parameters with enum values and descriptions, so the baseline is 3. The description enriches the 'action' parameter by explaining the real-world intent of each value, but it does not add material meaning for 'target' beyond what the schema states.

  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 a cache-management tool with specific operations: viewing statistics, cleaning expired entries, and clearing cache layers. This clearly distinguishes it from the sibling PubMed search tools, which perform content queries rather than cache maintenance.

  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 gives explicit guidance on which action value to use for each intended outcome: stats for hit rates/storage, clean for expired entries, clear for wiping a layer. There is no explicit 'when not to use' statement, but the distinction from sibling tools is evident and the action-level guidance is clear.

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