Server Quality Checklist

Tool Scores

• explore_repoA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: shows directory structure and optionally symbols, performance caching per git commit, accepts flexible types (int or string for several params), and provides detailed examples of output format. No destructive actions are implied, and it clarifies expected inputs like absolute root_path.

  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 long but well-organized with emojis, numbered workflow, examples, and pro tips. Every section adds value; however, some redundancy (e.g., repeated parameter types) could be trimmed. It is front-loaded with the main purpose and workflow, making it easy to grasp quickly.

  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 5 parameters, no annotations, and an output schema, the description covers all necessary input details and workflow guidance. The examples effectively illustrate expected output, and the output schema likely provides additional structure. The description addresses the complexity of progressive exploration thoroughly.

  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 coverage is 0%, but the description richly explains each parameter: root_path (absolute path requirement), max_depth (how deep, unlimited by default, accepts int/string), include_symbols (shows signatures, accepts bool/string), focus_dirs (top-level directories), and max_symbols_per_file (limit when symbols included). Examples demonstrate usage.

  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 maps a codebase structure starting simple then zooming in. It specifies 'explore_repo' as distinct from sibling tools 'find_symbol' and 'what_breaks' by focusing on directory and symbol overview rather than locating specific functions or analyzing breaks.

  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 a clear progressive discovery workflow (step 1-3), explicit when to use include_symbols, and advice on avoiding information overload. It also tells what to do next after exploring, giving contextual guidance on using focus_dirs or find_symbol.

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

• find_symbolA
  4.9/5.0
  Behavior5/5

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

  The description fully discloses behavior: uses fuzzy matching, returns a list of symbol objects with exact fields, empty list if no matches, and how to proceed with the output. No annotations exist, so the description carries the full burden well.

  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 clear sections (STEP, INPUTS, EXAMPLES, RETURNS, NEXT) and front-loaded with purpose. It is somewhat verbose but every sentence adds value, though could be slightly more concise.

  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 only 2 parameters and an output schema, the description is very complete. It explains the return format via example, the usage flow, and links to sibling tools, leaving no ambiguity.

  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 adds critical meaning: root_path must be the same absolute path from explore_repo, query examples are given. This 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 clearly states the tool's purpose: finding specific functions, classes, or methods in the codebase. It specifies the verb 'find' and the resource 'symbols', and distinguishes from siblings like explore_repo and what_breaks.

  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 AFTER explore_repo()' and 'Pick a symbol from the results and pass... to what_breaks()'. It also mentions fuzzy matching and gives practical examples.

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

• what_breaksA
  4.9/5.0
  Behavior5/5

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

  No annotations provided, so description fully discloses behavioral traits: it performs a text search for the name, lists potential false positives (comments, same names, strings), and notes it is not a dependency analysis. The 'IMPORTANT' section clearly warns about limitations.

  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?

  Description is structured with clear sections (INPUT, EXAMPLE INPUT, EXAMPLE OUTPUT, IMPORTANT) and front-loaded with purpose. While thorough, it is somewhat verbose (approx. 300 words) and could be slightly trimmed without losing clarity.

  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?

  Covers purpose, usage flow, input format, output structure with real example, and limitations. Despite lack of annotations and formal output schema, the example output and notes make the tool's behavior fully understandable for an 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?

  Schema coverage is 0% (only provides type: object with additionalProperties). Description compensates fully by specifying that the object must have at least 'name' and 'path' keys, and provides a concrete example with all relevant fields. This adds significant meaning beyond the 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?

  Description starts with 'See what code might break if you change this symbol' and explicitly states it shows every place the symbol name appears. Clearly distinguishes from siblings find_symbol (which finds symbols) and explore_repo.

  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?

  Directly instructs 'USE THIS AFTER find_symbol()' and provides step context 'STEP 3'. Includes detailed example of chaining with find_symbol and explicit input requirements.

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