Server Quality Checklist

Tool Scores

• gemini_infoB
  3.4/5.0
  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 implies read-only behavior through terms like 'diagnostics' and 'list', but fails to disclose output formats, error conditions, or whether these operations are cached/live. It meets minimum expectations for a metadata tool but lacks 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 a single, efficient sentence that front-loads the category ('Gemini CLI diagnostics') and follows with a colon-delimited list of specific capabilities. No words are wasted.

  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 single-parameter tool with complete schema coverage, the description is adequate. It covers the primary use cases (though misses list_models in prose). No output schema exists, but the description sufficiently indicates the return type nature (diagnostic info).

  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?

  With 100% schema coverage, the baseline is 3. The description maps most enum values to user-friendly intents (ping→connectivity, etc.) but omits 'list_models' entirely. It adds minimal semantic value beyond what the schema's detailed descriptions already provide.

  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 identifies the tool's purpose using specific verbs (check, get, list) and identifies the resource (Gemini CLI diagnostics). It implicitly distinguishes from sibling 'gemini_query' by focusing on introspection/metadata rather than active querying, though explicit differentiation would strengthen this further.

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

  Usage Guidelines2/5

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

  The description lists capabilities but provides no explicit guidance on when to use this tool versus 'gemini_query'. It lacks prerequisites (e.g., 'use ping to verify connectivity before querying') or exclusion criteria that would help an agent select the correct tool.

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

• gemini_queryA
  3.9/5.0
  Behavior3/5

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

  With no annotations, description carries full burden. It discloses authentication method (locally authenticated CLI), safety controls (sandbox, yolo, approval modes), and file referencing (@path). However, misses return format, error behavior, and side effects of auto-approve modes.

  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?

  Front-loaded with core purpose, followed by model support, file syntax, and options list. Efficiently packs 8 parameters worth of context into four brief statements. Minor deduction for the slightly telegraphic 'Options:' list which could flow better.

  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?

  Covers key capabilities well for a complex 8-parameter tool: authentication, model flexibility, file inclusion, workspace directories, and safety modes. Absence of output schema is mitigated by clear description of what the tool does, though mention of return format would improve completeness.

  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?

  Adds conceptual value beyond 100% schema coverage by explaining @path syntax for file references and grouping related boolean flags (sandbox, yolo) under 'Options'. Schema handles individual parameter docs; description provides usage context.

  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?

  States specific action (Send), resource (prompt to Google Gemini), and mechanism (locally authenticated CLI). Clearly distinguishes from sibling 'gemini_info' by focusing on active querying vs. information retrieval.

  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?

  Implies usage through 'Send a prompt' and lists capabilities, but lacks explicit guidance on when to use gemini_info instead, or when-not-to-use scenarios (e.g., when file contexts are inappropriate).

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