Server Quality Checklist

Tool Scores

• repolens_find_classesA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that ast-grep is used and that matching is structural rather than regex-based, which is useful. But beyond that, it mostly restates what annotations and the schema already make clear.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is front-loaded with a clear summary and uses well-organized sections. However, the Args list largely duplicates the input schema for all seven parameters, making the definition longer than necessary. The examples and wildcard notes earn their place, but roughly half of the content is redundant with structured data.

  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?

  The tool has no required parameters, all parameters are documented in the schema, and an output schema exists. The description supplies enough context for normal usage: it explains ad-hoc paths, wildcards, defaults, and gives examples. It does not explain return format details, but that is covered by the output schema. The main missing piece is explicit alternative routing, already accounted for under usage guidelines.

  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 schema carries the baseline documentation. The description adds genuine value by explaining wildcard support for the name parameter, providing default values inline, and giving concrete invocation examples. A minor omission is that the language parameter description omits the ts/js aliases present in the schema, but the schema itself remains authoritative.

  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 a specific verb (Find), resource (class definitions across repositories), and method (AST analysis). It also mentions that it finds PHP traits, which distinguishes it from sibling tools like find_functions and find_types. The alignment between name, title, and description is strong.

  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?

  Provides clear usage context: searches class declarations, supports ad-hoc paths without registration, and offers repo/language filtering. It gives three concrete examples. However, it never explicitly names alternative tools or states when not to use this tool, so it stops short of full guidance.

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

• repolens_find_api_routesA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive behavior, and the description consistently supports that by describing a search-only operation. It adds useful behavioral context beyond annotations, including supported frameworks, the fact that paths require no registration, and default output settings. Minor unspecified details like error behavior or exact route-detection limitations are acceptable given the annotations and output schema.

  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 opening statement, Supported Frameworks section, Args list, and Examples, making it easy to scan. The Args section is somewhat redundant with the fully-described input schema, which prevents a perfect score, but the overall length is appropriate and front-loaded.

  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 read-only search tool with an output schema, rich parameter descriptions, and strong annotations, the description is thorough: it covers scope, supported frameworks, filtering modes, ad-hoc paths, defaults, output format, and practical examples. Nothing an agent needs to decide whether to invoke this tool or how to invoke it correctly is missing.

  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?

  The input schema already has 100% parameter description coverage, so the baseline is 3. The description's Args section largely restates the schema rather than adding new meaning, though the examples do illustrate how parameters can be combined effectively. This is adequate but not additive enough to warrant a higher score.

  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 the specific, action-oriented purpose: 'Find API route/endpoint definitions in backend code across repositories.' It names the exact resource type (HTTP route definitions) and supported frameworks (Express, Fastify, NestJS, Laravel), which clearly distinguishes it from sibling tools like repolens_find_functions and repolens_find_classes.

  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 gives clear context on what the tool searches and how to scope it, and the examples demonstrate concrete invocation patterns such as searching a directory directly with paths or filtering by repoFilter and method. It does not explicitly mention alternative sibling tools or state when not to use this tool, so it falls just short of a perfect score.

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

• repolens_find_functionsA
  4.2/5.0
  Behavior4/5

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

  Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds useful behavioral detail: AST-based structural matching via ast-grep, support for ad-hoc paths without registration, wildcard/filter behavior, and default result limits. It does not dwell on return shape, but the output schema covers that.

  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 front-loaded with the tool's core purpose and then organized into Args and Examples sections, making it easy to scan. It is slightly longer than necessary because the Args list duplicates schema descriptions, but the structure and examples justify the length.

  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 complete for a search tool: it states what is searched, how matching works, all parameter roles with defaults, and multiple worked examples. With annotations covering safety and an output schema defining return values, nothing essential is missing.

  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?

  Schema description coverage is 100%, and each parameter already has a description, enum, or default in the input schema. The description's Args section mostly restates that information, though it adds a few clarifying details and concrete usage examples.

  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 and resource: 'Find function and method definitions across repositories using AST analysis.' It further narrows the scope to function declarations, arrow functions, and class methods in JS/TS and PHP, which clearly separates it from sibling tools like find_classes, find_types, and find_api_routes.

  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 provides clear context for when to use the tool — searching for functions and methods — and offers examples for ad-hoc directory searches, wildcard matching, and repository filtering. It does not explicitly state when to prefer sibling tools, but the scope is evident and the examples demonstrate common usage patterns.

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

• repolens_list_repositoriesA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare this read-only, idempotent, non-destructive, and bounded to the configured world. The description adds meaningful context beyond those annotations by revealing that the data comes from repolens.yaml and that the response includes aliases, paths, and git branch information.

  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 compact and front-loaded: the first sentence states the core behavior, the second adds the return-value detail, and the Args section is minimal. Every component earns its place, and there is no fluff or unnecessary elaboration.

  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 simple listing tool with no output schema, the description is sufficiently complete: it names the data source, the returned fields, and the only parameter. The annotations cover behavioral safety, so nothing an agent needs to invoke it correctly is missing.

  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?

  The schema describes the single 'response_format' parameter fully with an enum and a default of 'markdown', giving 100% schema coverage. The description's Args section largely repeats this information, adding no meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

  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 precise action ('List all configured repositories') and a clear resource, and it immediately frames the purpose as enabling cross-repository search. The sibling tools are all find_* operations over code symbols, so 'list repositories' is distinguishable without ambiguity.

  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 phrase 'available for cross-repository search' gives clear context for when an agent would call this tool: to discover the repository scope before searching. It does not explicitly name alternatives or exclusions, but the intended use case is evident and the sibling distinction does not require further clarification.

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

• repolens_find_typesA
  4.7/5.0
  Behavior5/5

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

  The description goes beyond the readOnly/idempotent annotations by disclosing AST-based matching via ast-grep, PHP's lack of type aliases, wildcard support, and the fact that paths need no registration. It also documents defaults for exportedOnly, maxResults, and response_format. No statement conflicts with the annotations.

  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 front-loaded with a clear summary, followed by a well-organized argument list and concrete examples. Given the 7 optional parameters, the length is appropriate and every section serves a purpose. There is no generic filler or redundant boilerplate.

  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 an output schema, so return-value details need not be repeated. The description covers all key dimensions: search targets, language filters, repo vs. ad-hoc path selection, export filtering, result limits, and response format. An agent has enough information to invoke the tool correctly without additional assumptions.

  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 already covers all 7 parameters, so the baseline is 3, but the description adds meaningful semantics: wildcard patterns like '*Props', ad-hoc paths with no registration, and default values for optional fields. The examples map parameters to realistic calls. The only minor gap is not restating the 'ts'/'js' language aliases in prose, but those are already in 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?

  The description opens with a specific action: finding type aliases and interface definitions via AST analysis. It clearly distinguishes the tool from siblings such as find_classes and find_functions by targeting type/interface declarations. The scope is unmistakable due to language-specific details like PHP's lack of type aliases.

  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 gives concrete invocation examples, including ad-hoc directory searches, wildcard patterns, and exported-only searches. This provides clear context for how to run the tool. However, it does not explicitly contrast it with sibling tools or state when to prefer find_types over find_classes/find_functions, leaving some routing to inference.

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