Server Quality Checklist

Tool Scores

• reload_keysA
  3.8/5.0
  Behavior2/5

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

  No annotations exist, so the description must fully convey behavior. It states it reloads keys but does not disclose side effects (e.g., overwriting, errors), success/failure indications, or whether it affects running requests. This is insufficient for a mutation.

  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 one sentence, front-loaded with the verb 'Reload', and contains no filler. Every word is necessary.

  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 zero parameters and an output schema present, the description adequately covers the key details (sources). However, it could mention that it returns a success status or errors, but given simplicity, it is nearly 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?

  There are zero parameters, so the schema provides complete coverage. The description adds value by naming the exact sources (~/.gemini-tts-mcp/keys.json and env vars), which is more specific than the empty schema.

  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 states the action (reload API keys) and the specific sources (file or env vars). It differentiates from sibling tools (generate speech, list voices) which serve completely different purposes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use (after updating keys), but does not explicitly state when not to use or provide alternatives. The context is simple, so no exclusion is needed, but guidance is minimal.

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

• list_voices_by_genderA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It mentions returning a formatted table, which is helpful, but it does not disclose whether the operation is read-only, any authentication needs, or potential side effects. Given the tool's simplicity, this is acceptable but not exceptional.

  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 exceptionally concise (two sentences plus structured Args/Returns) with no superfluous content. The purpose is front-loaded, and each line serves a clear function.

  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 one required parameter, no annotations, but an output schema assumed to exist, the description adequately covers purpose, parameter semantics, and return format. It omits error handling or empty result behavior, but for a simple filter tool, it 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?

  The schema description coverage is 0%, but the description's Args section explains the gender parameter accepts 'male' or 'female' (case-insensitive), adding meaningful semantics beyond the raw schema. This compensates well for the lack of 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 clearly states the tool lists Gemini TTS voices filtered by gender, with a specific verb and resource. It distinguishes from the sibling list_voices (which likely lists all voices) by adding the gender filter.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage (when you need voices of a specific gender) but does not explicitly state when to use this vs. list_voices or provide exclusions. Sibling context helps but is not leveraged in the description.

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

• list_voicesA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It explains that voices are multilingual and can be filtered, but it does not disclose any potential behavioral traits such as pagination, rate limits, or data freshness. For a simple listing tool, this is adequate but not outstanding.

  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: two sentences plus clearly labeled Args and Returns sections. Every sentence adds value, and the structure is easy to parse.

  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 tool with only two optional parameters and an existing output schema, the description is mostly complete. It notes the return is a 'formatted table', but could be slightly more specific about the exact fields in the output. Nonetheless, it covers the essential context.

  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%, yet the description adds significant value by explaining both parameters with examples and case-insensitivity. For filter_tone, it lists acceptable tone names, which is more informative than the schema 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 clearly states the action ('List') and resource ('all Gemini TTS voices') and specifies that it includes gender, tone, and description. It distinguishes from sibling 'list_voices_by_gender' which likely only filters by gender, whereas this tool also supports tone filtering.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description indicates that filtering is optional and provides examples of filter values. However, it does not explicitly state when to use this tool versus the sibling 'list_voices_by_gender', nor does it provide guidance on 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.

• pool_statusA
  4.3/5.0
  Behavior4/5

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

  No annotations exist, but the description accurately conveys a read-only operation checking configured keys, which is sufficient for a simple tool with no side effects.

  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?

  A single, efficient sentence that is front-loaded and contains no unnecessary words.

  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 parameterless tool with an output schema, the description completely captures the tool's purpose and behavior.

  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 zero parameters, the description adds value by specifying what is checked (API key count), going beyond the empty schema.

  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 states the action ('Check') and the resource ('API keys'), and distinguishes it from sibling tools focused on speech generation and key reloading.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit usage guidelines are provided, but the purpose is simple and obvious, making it adequate for a straightforward status check.

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

• generate_speechA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses key behaviors: multilingual support, API key rotation, model fallback, style instruction prepending, pitch adjustment, and error return. It does not mention destructive nature or auth requirements, but for a TTS tool, this is sufficient.

  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-structured: a brief intro, then a bullet-style Args list, then a Returns line. Every sentence adds value with no 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's moderate complexity (6 params, 1 required) and the presence of an output schema, the description covers all necessary information: functionality, parameter details, and return type. It is fully self-contained.

  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?

  The input schema has 0% description coverage, but the description's Args section explains every parameter (text, voice_name, style_instruction, pitch_factor, model, output_path) with defaults and usage details, fully compensating 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 clearly states the tool generates speech audio from text using Gemini TTS. It mentions the key parameters and distinguishes itself from siblings (list_voices, etc.) by focusing on generation, not listing or management.

  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 explains the tool's behavior (rotates API keys, falls back between models) and implicitly tells when to use it (for generating speech). It cross-references list_voices for browsing voices, but does not explicitly 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.