Server Quality Checklist

Tool Scores

• cpl_searchA
  4.7/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is already clear. The description adds valuable behavioral context: full-text search semantics, pagination (offset 1-based), output format differences (markdown vs json), the 'Error:' prefix on failure, and the suggestion to follow up with cpl_lookup_section. This is more than minimal, though it doesn't discuss rate limits or underlying API 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 well-structured with a clear opening sentence, a usage paragraph, a compact Args section that parrots the schema but adds examples and defaults, a Returns section that documents the JSON shape, and a short Examples list. No wasted words; every sentence earns its place.

  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?

  The tool has only one required parameter (wrapped in SearchInput) and a comprehensive output schema. The description covers the tool's purpose, usage boundaries, parameter nuances, return format details, error behavior, and follow-up action. This is complete for an agent to select and invoke the tool correctly without additional context.

  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?

  The input schema is detailed with descriptions for each parameter, but the description adds extra semantic value: it explains the purpose of 'term' with examples ('automatic discovery', 'speedy trial'), clarifies the offset as 1-based, notes default values, and describes the response_format as 'markdown' (default) or 'json'. Since schema coverage is 0% by the context signal (though schema itself has param descriptions), the tool description compensates well by restating and enriching parameter meaning.

  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 a specific verb ('Full-text search') and resource ('New York Criminal Procedure Law (CPL)'), and clearly distinguishes from the sibling tool by noting 'use cpl_lookup_section' when the section number is already known. It also conveys the ranked-list return behavior.

  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 says when to use: when the user describes a topic rather than naming a section, with concrete example queries. It also states when not to use: when the section number is known, directing to cpl_lookup_section. This exceeds the 'clear context, no exclusions' threshold.

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

• cpl_lookup_sectionA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond this: input normalization ('Leading "CPL", "section", and "§" are stripped automatically'), return format details (markdown vs. json with full object schema), and error behavior ('On failure, a string beginning with "Error:"'). No contradiction with annotations.

  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 well-structured with a clear lead sentence, separate Args, Returns, and Examples sections. It is fairly long but every section provides necessary information for correct tool usage; it only slightly duplicates schema details.

  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?

  The description is fully self-contained: it covers input normalization, output format, return schema, error handling, and differentiation from the sibling tool. Given the tool's moderate complexity and the presence of an output schema, the description leaves no gaps for an AI agent.

  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?

  Although the schema includes detailed descriptions for both parameters, the description reinforces and clarifies them with concrete examples of valid citations ('245.20', 'A245', 'T1') and the expected response_format values. It also explains the output schema in plain language, which goes beyond the schema's field descriptors.

  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 ('Retrieve') and resource ('full text of a single New York Criminal Procedure Law location by citation'), making the tool's exact function clear. It also explicitly distinguishes itself from the sibling tool cpl_search by stating 'It does NOT search by topic — use cpl_search for that.'

  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?

  The description provides explicit when-to-use guidance ('Use this when the user names a specific CPL section or article'), when-not-to-use ('Don't use when: 'Which CPL section covers discovery?''), and names the alternative tool (cpl_search). It also includes concrete examples of user utterances and corresponding citation values.

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