Server Quality Checklist

Tool Scores

• search_songsA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnly/idempotent/destructive safety, and the description adds valuable behavioral context: the underlying lyrics.com search matches titles and lyrics together, so results are locally ranked/filtered, and match='strict' filters further. This goes beyond annotation-only info.

  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 slightly long (5 sentences) but every clause earns its place, front-loading purpose and then adding usage and behavioral nuance. No waste, though the final sentence could be split for readability.

  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?

  With an output schema and strong annotations, the description covers the key functional details: return fields, use cases, and the caveat about title matching. Minor gaps remain (e.g., pagination behavior, potential errors), but the description is adequate for safe invocation.

  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 moderate (60%) and descriptions for title and match exist. The description adds meaning by explaining artist narrows results and elaborating the effect of match='strict', which compensates for undocumented page/limit/artist and ties parameters to behavior.

  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 ('Find'), resource ('songs on lyrics.com'), and scope ('by their title'), and clearly distinguishes from siblings by mentioning its role in preparing to call get_lyrics and differentiating covers/versions.

  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?

  It explicitly says 'Use this when someone names a song...' and gives a second use case (distinguishing covers). It does not explicitly contrast with the sibling search_lyrics, but the guidance is clear enough for selection.

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

• get_lyricsA
  4.7/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint, idempotentHint), the description adds crucial behavior: truncated responses, the need to check 'truncated' and use 'offset' with 'next_offset', the valid 'no_lyrics' status with empty lyrics, and a citation requirement. This significantly enhances the agent's understanding of the tool's runtime behavior.

  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 four sentences, each earning its place: main purpose, truncation handling, no_lyrics edge case, and citation requirement. It is concise yet information-dense, with no redundant phrasing.

  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 covers the full usage workflow: obtaining the id/url, handling long lyrics through pagination, dealing with legitimate no_lyrics responses, and citing sources. Combined with the provided output schema and sibling context, it is comprehensive for an AI agent.

  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 meaning by explaining the pagination pattern (offset + next_offset) and tying id/url to sibling search tools, which is useful context beyond the raw schema 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 states a specific action: 'Fetch the full lyrics of one song from lyrics.com' given a song id or URL. It clearly distinguishes from sibling search tools by focusing on retrieving a single song's lyrics using identifiers returned by search tools.

  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 specifies that input comes from search_lyrics or search_songs, giving clear context for when to use this tool. It also explains the pagination workflow and that no_lyrics is a valid outcome, though it does not explicitly provide when-not-to-use exclusions.

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

• search_lyricsA
  4.7/5.0
  Behavior5/5

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

  Beyond the readOnly/idempotent annotations, the description reveals that lyrics.com returns loose and title-only matches, so results are locally filtered to keep only genuine matches. It also explains pagination behavior ('One call returns one page... increase page rather than limit') and the impact of verify='none' to see the raw unfiltered list, offering rich behavioral 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 five sentences, each serving a purpose: purpose, return content, usage scenario, pagination semantics, and filtering behavior. It is front-loaded with the core action and contains no extraneous words 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?

  Given the tool has 5 parameters and an output schema, the description still provides a complete overview: what is returned, when to use it, how pagination works, how filtering works, and how verification options affect results. It leaves no major questions about invocation or expectations.

  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?

  With 100% schema description coverage, the baseline is 3. The description adds value by clarifying the functional difference between 'page' and 'limit' and by explicitly describing the effect of verify='none', which is not fully captured by the schema's parameter descriptions alone.

  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 'Search lyrics.com for songs whose lyrics contain a given word or phrase,' which is a specific verb, resource, and scope. It clearly differentiates from siblings by mentioning that the returned id and URL are needed to fetch full text with get_lyrics, positioning search_lyrics as the lookup-by-lyric tool.

  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 this when someone remembers a fragment of lyrics but not the song, or wants songs mentioning a word or theme.' It also provides page/limit usage guidance, but does not explicitly name search_songs as the alternative for title-based searches, which would have made it a 5.

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