Server Quality Checklist

Tool Scores

• get_mesh_treeA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full disclosure burden. It excellently documents the return structure (ui, label, treeNumbers, categories, broader) and provides the complete MeSH category taxonomy (A-Z), which is crucial behavioral context. Lacks explicit mention of read-only/idempotent nature, though implied by 'Retrieve' and tool name.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is comprehensive and well-structured with clear headers. While lengthy due to the 16-line MeSH category reference list, this domain-specific reference material earns its place by enabling the agent to interpret returned category codes. No redundant or wasted sentences.

  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?

  Despite having no output schema and 0% input schema coverage, the description achieves completeness by documenting the full return structure (including nested object shapes) and parameter semantics. The inclusion of MeSH category mappings provides essential domain context for interpreting results.

  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 documenting the 'descriptor' parameter with type (str), format (MeSH UI code), concrete example ('D003920'), and provenance context ('returned by search_mesh'), enabling correct invocation.

  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 explicitly states what the tool retrieves (MeSH tree hierarchy, tree numbers, top-level categories, parent descriptors) using specific verbs. It clearly distinguishes this from sibling tools by focusing on hierarchical relationships rather than searching (search_mesh) or record details (get_mesh_record).

  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 when-to-use guidance ('Use this to understand where a heading sits... helping to determine whether the heading is specific enough'). While it doesn't explicitly state when NOT to use it or name sibling alternatives, it implies the workflow by referencing that the descriptor parameter comes from 'search_mesh'.

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

• get_mesh_qualifiersA
  4.7/5.0
  Behavior5/5

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

  Excellent disclosure given no annotations exist. It explicitly warns about performance costs ('Makes up to 34 additional HTTP requests'), documents API limitations ('NLM public API does not expose qualifier abbreviations'), and details the exact return structure including optional keys, providing necessary behavioral context beyond what annotations would typically cover.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Structured clearly with Parameters/Returns sections. While lengthy, every sentence serves a purpose given the lack of schema documentation and output schema. The technical details (MARC formatting, HTTP request counts) are essential for correct usage, justifying the length despite the density.

  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?

  Thoroughly complete for a tool with no output schema and no annotations. It documents the return dictionary structure, explains domain-specific concepts (MeSH qualifiers vs. headings), provides usage constraints, and includes practical cataloging guidance (MARC subfield construction).

  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 (only titles provided), the description fully compensates by documenting both parameters in detail: descriptor includes format examples ('D003920') and provenance ('returned by search_mesh'), while include_annotations explains the side effects, cost, and default value.

  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 the specific action and resource ('Retrieve the allowable subheading qualifiers for a MeSH descriptor') and distinguishes from siblings by focusing narrowly on qualifiers/subheadings versus records or trees. It clarifies the domain-specific concept with concrete examples ('Diabetes Mellitus/therapy').

  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 workflow context by noting the descriptor parameter can be 'returned by search_mesh', establishing a tool chain. It explicitly warns when to use the include_annotations flag ('use only when you need the annotation text'). However, it does not explicitly contrast with siblings get_mesh_record or get_mesh_tree to clarify when to prefer this tool over those alternatives.

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

• get_mesh_recordA
  4.7/5.0
  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. It effectively discloses the read-only retrieval nature and comprehensively documents the return structure (ui, uri, treeNumbers, etc.). Minor gap: no mention of error handling (e.g., invalid UI codes) or rate limiting, though the data structure documentation is thorough.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Well-structured with clear front-loading of purpose and usage. The Returns section is lengthy, but justified given the absence of a structured output schema (Has output schema: false). The cross-references to sibling tools are efficiently integrated.

  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 rich return structure and lack of output schema/annotations, the description achieves completeness by documenting all return fields, providing parameter examples, and mapping tool relationships. Nothing critical is missing for agent invocation.

  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?

  Critical compensation for 0% schema coverage. The description provides exact format ('MeSH UI code'), concrete example ('D003920'), and provenance context ('returned by search_mesh'), fully explaining the parameter semantics that the schema omits.

  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?

  Excellent specificity: 'Retrieve a full MeSH descriptor record' clearly states the verb and resource, and enumerates specific content included (scope note, tree numbers, broader descriptors, see-also references). The workflow distinction from search_mesh ('Use this after search_mesh') further sharpens the scope.

  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?

  Explicit temporal guidance ('Use this after search_mesh') establishes clear prerequisites. It also references sibling tool get_mesh_qualifiers for related functionality ('full list via get_mesh_qualifiers'), creating a clear mental model of the tool ecosystem.

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

• search_meshA
  4.7/5.0
  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 identifies the external endpoint ('NLM Lookup autocomplete'), documents default behaviors (startsWith matching, limit 10), and details the return structure including error handling and field definitions ('ui', 'uri'). Minor gap: does not explicitly state rate limits or timeout behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Uses a structured docstring format (Parameters/Returns sections) that efficiently organizes information. The purpose and usage guidelines are front-loaded in the first two sentences. The Returns section is necessary given the absence of an output schema, though it adds length. No redundant or tautological statements.

  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 zero schema descriptions and no output schema, the description provides comprehensive coverage: parameter semantics, return value structure, sibling relationships, and endpoint details. The inclusion of example values and URI formats (e.g., 'http://id.nlm.nih.gov/mesh/D003920') provides sufficient context for an agent to invoke the tool correctly without additional discovery.

  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%, requiring the description to fully compensate. It excellently documents all three parameters: query includes realistic examples ('diabetes', 'neoplasms'), match explains all three enum-like options with behavioral context ('analogous to LCSH suggest2'), and limit specifies constraints ('max 50'). Completely compensates for the schema's lack of 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 opens with a precise action ('Search MeSH descriptors'), resource ('MeSH descriptors'), and method ('NLM Lookup autocomplete endpoint'). It clearly distinguishes itself from siblings by stating it finds codes 'before calling get_mesh_record or get_mesh_qualifiers', establishing the correct workflow sequence.

  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?

  Explicitly states when to use the tool ('Use this to find the MeSH UI code and URI...') and names specific sibling alternatives to use afterwards ('before calling get_mesh_record or get_mesh_qualifiers'). This provides clear workflow guidance and prevents incorrect tool selection.

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