Server Quality Checklist

Tool Scores

• dependency_impactA
  4.4/5.0
  Behavior4/5

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

  With no annotations available, the description carries the full burden of behavioral disclosure. It reveals the underlying mechanism (ripgrep for candidates, tree-sitter AST for classification) and classifies usage types (call/import/definition/type_reference). This is substantive and goes beyond a simple 'find usages', though it does not mention side effects or performance caveats.

  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 for purpose, usage, params, and returns. It is slightly longer than necessary but every sentence adds value—no filler. The front-loaded purpose sentence ensures immediate comprehension. A 5 would require even tighter phrasing without losing the useful details.

  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 5-parameter tool with no output schema and no annotations, this description is highly complete: it explains the input parameters, the return structure, the use case, and the filesystem-based requirement. It lacks only minor edge-case details (e.g., error handling, behavior with no matches), but overall it equips the agent well for correct invocation.

  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%, so the description must compensate for the bare schema. It does so excellently with an Args section that explains each parameter including optional behavior (file_glob, whole_word default, max_results cap). The return structure is also documented, providing far more meaning than the schema's property titles 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 a clear, specific verb and resource: 'Find everywhere a symbol is used in a checked-out repo (the blast radius).' It further explains the value for code review, making the tool's purpose unmistakable and distinguishing it from sibling tools like code_search or trace_call_chain.

  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 when-to-use guidance ('before you approve a change... see who depends on it') and an explicit when-not ('point it at a LOCAL clone... not the MR URL'). However, it does not directly compare to alternative sibling tools, or say when another tool would be more appropriate, so it stops short of a 5.

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

• mr_review_statusA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It states 'Pure data, no LLM' and 'Collapses several platform API calls into one snapshot,' disclosing that it is a read-only aggregator. It also details the return structure, but omits potential performance implications or error behavior, so a 4 is appropriate.

  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. It opens with a clear purpose sentence, adds key differentiators, then presents args and returns in a scannable format. No unnecessary words or redundancy.

  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 single-parameter read-only tool with no output schema, the description is quite complete. It lists all return fields, notes the aggregated nature, and provides usage context. It could mention auth requirements or failure scenarios, but these are probably less critical for this tool type.

  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 schema lists a single 'url' parameter with no description, and schema coverage is 0%. The description fully compensates by defining it as a 'Full GitLab merge request URL,' which clarifies the expected input beyond the schema's bare type definition.

  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 the tool gets a merge request's review status, specifically metadata, discussions, and resolution. It also distinguishes from siblings by describing it as a single snapshot that collapses several API calls, making it clear this is an overview tool rather than a diff-focused one.

  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 directive 'Start here to orient before diving into the diff' provides clear usage context, suggesting this is the first tool to use when reviewing a merge request. However, it does not explicitly name alternatives or state when not to use it, stopping short of a 5.

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

• code_searchA
  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 the full burden. It discloses the underlying mechanism (Ollama embedding, vector + FTS search with RRF reranking), critical dependencies, and the error return format. This is substantial, but it omits potential latencies or side effects (though as a search tool, side effects are minimal). Still, it covers the essential behavioral traits.

  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 well-structured and efficient: a one-line summary, followed by a brief mechanism explanation, usage guidance, prerequisites, and then clearly labeled Args/Returns sections. Every sentence adds value without redundancy, making it appropriately sized for the tool's complexity.

  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 provides a complete picture for an agent: purpose, usage, prerequisites, detailed parameter semantics, return structure, and error handling. Without an output schema, it still specifies result fields. It covers all necessary operational context, making it ready for reliable invocation.

  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 schema has 0% description coverage, but the description's 'Args' section thoroughly explains each parameter: query as natural language or code snippet, root as absolute path, and k as max results with default. This fully compensates for the missing schema descriptions and adds practical guidance.

  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 'Hybrid semantic + full-text search over an indexed local repository,' which is a specific verb and resource. It clearly distinguishes itself from siblings by focusing on repository search, unlike tools for trace calls or MR diffs. The explicit use case ('find existing patterns, conventions, or examples') further reinforces its unique purpose.

  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: 'Use this to find existing patterns, conventions, or examples in the codebase before reviewing a new implementation.' It also states prerequisites (Ollama running, index_repo executed). However, it does not explicitly mention when not to use it or name alternative tools, so it falls just short of a 5.

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

• index_statusA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it explains freshness is keyed to the git commit, what 'stale' means, and the error condition when the semantic extra is not installed. It does not define 'model_mismatch' or discuss resource implications, which leaves a small transparency gap.

  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?

  Every sentence earns its place: purpose, freshness semantics, actionable usage guidance, then args and returns. It is front-loaded with the core question and uses clear formatting for skimming.

  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?

  There is no output schema, but the description lists all return fields (state, root, chunks?, indexed_at?, etc.) and the error form. Combined with usage guidance and error handling, a one-parameter status tool is fully covered.

  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 only declares root as a string, so the description's 'Absolute path to the repository' adds meaningful semantics. Since schema coverage is 0%, this compensation is important and mostly sufficient for a single parameter.

  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: 'Report whether a repo's semantic index is fresh, stale, or absent.' It clearly distinguishes itself from sibling tools by framing it as a pre-flight check before using code_search or mr_review_context, and contrasts with index_repo which performs the indexing.

  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 explicitly says 'Check this before leaning on semantic results (code_search / mr_review_context)' and instructs the agent to 'offer to index_repo(root) first' if state is stale or model_mismatch. This gives direct when-to-use guidance and names the relevant alternatives.

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

• mr_verify_reviewA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full transparency burden. It discloses read-only behavior, explains the join logic, defines the notion of 'addressed', and details the GitHub limitation regarding thread resolution. This is exemplary behavioral disclosure.

  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 well-structured and front-loaded with the purpose. Each section (purpose, args, returns) earns its place. The returns block is detailed but necessary given the absence of an output schema, so there is no waste.

  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 tool with two parameters, no annotations, and no output schema, the description is fully complete. It explains the algorithm, the return structure, platform differences, and the intended use case, leaving no meaningful gaps.

  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 fully documents both parameters: url as 'Full merge/pull request URL' and window as 'Lines before/after the commented line to scan (default 40).' This adds complete meaning beyond the bare schema names.

  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+resource: 'Check whether each review thread was addressed by nearby diff changes.' This clearly distinguishes the tool from siblings like mr_review_status or mr_diff_lines by focusing on verification of thread resolution against diff context.

  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 usage context: 'a fast re-review pass without re-reading the whole diff.' It also notes a platform-specific caveat for GitHub. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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

• trace_call_chainA
  4.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well by disclosing the AST/Tree-sitter approach, local-repo requirement, and returning parse_errors stats. However, it does not explicitly state whether the tool is read-only or mention limitations like language support coverage, which prevents a perfect score.

  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 well-structured with a purpose statement, a comparative paragraph, and clearly separated Args and Returns sections. It is appropriately sized for a tool with four parameters and a structured return value, with no wasted 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?

  The description is complete for its complexity: it provides the tool's purpose, a contrast with siblings, all parameter semantics, and an explicit return format. Because there is no output schema, the detailed return object fills the gap and makes the tool's behavior predictable.

  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%, so the description fully compensates. It defines symbol as a function/class name, root as an absolute path, language as an optional restriction with auto-detection, and max_depth as the number of caller/callee levels with a default of 1. This is exactly what an agent needs.

  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+resource+method: 'Trace a function's callers and callees across a checked-out repo (AST)'. It also explicitly contrasts with dependency_impact, stating that dependency_impact lists references while this tool builds a directed call graph, making the purpose unmistakable.

  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 names dependency_impact as a complementary alternative and clarifies when to use this tool: 'to reason about a change's ripple effects'. It also states a key prerequisite ('point it at a LOCAL clone'), which is practical usage guidance.

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

• mr_changed_filesA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and meets it: it discloses the output has no diff content, explains the reviewability flag and skip reasons, and specifies file ordering (reviewable-first then largest-change-first). It also provides the return shape.

  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?

  Description is front-loaded with a one-sentence purpose, then a compact rationale paragraph, then structured Args/Returns. Every sentence adds informational value with no filler.

  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 there is no output schema, the description compensates by itemizing the return object and file fields. It fully covers behavior, ordering, and integration with sibling tools, making the tool self-contained for an 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?

  The single parameter (url) receives a one-line semantic clarification ('Full GitLab merge request URL') beyond the bare schema, which is sufficient for a simple string param. It doesn't enumerate URL formats or error conditions, but it's adequate.

  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+resource ('List the files changed in a merge request with stats') and immediately contrasts with 'no diff content', differentiating it from sibling diff tools. The final line references mr_diff_lines for further filtering, reinforcing its distinct role.

  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?

  Explicitly frames it as 'the cheap entry point for large reviews,' defines the payload size advantage, and tells the agent to batch results into mr_diff_lines, giving a concrete when-to-use pattern and alternative.

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

• index_repoA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavior: incremental updates, full rebuild triggers, local Ollama requirement, environment variables, and return format including error handling. It also notes the per-repo LanceDB table, providing a complete picture of side effects and external dependencies.

  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?

  Although the description is detailed, it is well-structured with clear sections (behavior, prerequisites, args, returns). Every sentence adds value, with no repetition of schema information. It is front-loaded with the primary purpose and uses bullet-like formatting for Args and Returns.

  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 prerequisites, operational details, parameters, and return values, even without an output schema. It addresses the tool's complexity (incremental vs. full rebuild, external dependencies) and provides all necessary context for an agent to use it correctly.

  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 no descriptions for either parameter (0% coverage), but the description compensates fully: 'root: Absolute path to the repository to index' and 'force: Rebuild the whole index even if an up-to-date one exists.' This clarifies both the meaning and the expected values.

  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 function: 'Build or incrementally refresh a semantic search index for a local repository.' It specifies the resource (local repository), the action (build/refresh index), and the technical approach (AST chunking, Ollama embed, LanceDB storage). This distinguishes it from sibling tools like 'index_status' and 'code_search'.

  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?

  Provides explicit usage guidance: 'run it freely (e.g. when index_status reports "stale")' and explains when a full rebuild occurs ('changed embedding model or force=True'). It also states prerequisites (Ollama server, model pulled) and references the sibling tool index_status, making the choice of tool clear.

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

• mr_diff_linesA
  5/5.0
  Behavior5/5

  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 discloses bounded pagination via 'omitted_files' and 'truncated', noise-file handling via 'skipped_files', and default budget behavior for max_chars/skip_noise. This is thorough and non-contradictory.

  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 well-structured with a purpose sentence, behavioral guarantees, Args, and Returns. It is detailed but each sentence earns its place, front-loading the core purpose before diving into parameters.

  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?

  Even without an output schema, it lists the return object fields ({mr_number, ..., diff_shas, files[...], truncated, omitted_files, skipped_files, stats}) and explains the shape of line_mappings when lines_filter is used. This is complete for a complex diff tool.

  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 has 0% description coverage, but the Args section adds rich meaning to all five parameters: url format, files_filter as a targeted-fetch trigger, lines_filter producing compact line_mappings, max_chars as a token-safety budget, and skip_noise for lockfiles/generated/binary.

  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 opens with a specific verb and resource: 'Fetch a merge request's diff as structured, line-numbered hunks.' It further clarifies exact file paths, old/new line numbers, and diff content, distinguishing it from sibling tools like mr_diff_sections and mr_changed_files.

  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?

  Gives explicit guidance: 'For unknown-size MRs, call mr_changed_files first, then batch files_filter here.' It also explains when files_filter creates a targeted fetch and when max_chars/skip_noise are ignored, helping the agent choose the right mode.

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

• mr_diff_sectionsA
  5/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it explains AST-aware vs hunk-context-aware processing, guarantees that all changed lines are included, and details token-safety mechanics (bounded pages, omitted_files, truncated). It also clarifies how parameters like skip_noise and max_chars are ignored in targeted fetches, adding significant 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 well-structured with clear paragraphs and a compact Args/Returns format. Every sentence adds substantive information—purpose, differentiation, usage guidance, behavior, and parameter semantics—with no filler 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's complexity (symbol grouping, multiple modes, safety guarantees) and absence of an output schema, the description provides a complete picture: it explains the algorithm, return structure, parameter behaviors, and fallback strategies. It is self-sufficient for an agent to invoke correctly.

  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 zero descriptions, but the description's 'Args:' section thoroughly explains each of the 5 parameters, including defaults, edge cases (e.g., files_filter disabling noise-skip), and the meaning of include_context_lines. This fully compensates 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 opens with 'Fetch a merge request's diff grouped by enclosing function/class, not raw hunks,' which is a specific verb+resource+scope statement. It explicitly distinguishes itself from raw hunks and names a sibling tool (mr_diff_lines), making differentiation clear.

  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?

  It explicitly states when to prefer this tool over mr_diff_lines ('Prefer this over mr_diff_lines on a large MR...') and provides a workflow suggestion: 'For unknown-size MRs, call mr_changed_files first, then batch files_filter here.' It also describes the targeted fetch behavior for files_filter, giving clear use cases and alternatives.

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

• mr_post_commentsA
  5/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: it mutates state, posts one comment at a time from a queue, has no drafts/bulk-publish, retries transient failures with exponential backoff, and handles partial progress. It also states cross-platform behavior for GitLab and GitHub, providing crucial operational 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 long but every sentence adds value: behavioral notes, usage restrictions, prerequisites, parameter semantics, and return shape are all included without redundancy. The structured Args/Returns layout improves scannability.

  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 no output schema, so the description compensates by providing a full return value breakdown. It also covers error output, batching guidance, and failure semantics, making the description complete enough for an agent to confidently select and invoke the tool.

  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?

  Even though the input schema has 0% description coverage, the description's Args section explains each parameter in detail: url is the full merge/pull request URL, comments is a list of objects with optional fields, and max_comments is a safety cap. It also clarifies which comment fields are required or optional.

  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 begins with a specific verb and resource: 'Post inline review comments to a merge/pull request.' It also explicitly flags the write nature ('WRITE — this mutates the review'), which clearly distinguishes it from read-only siblings like mr_diff_lines and mr_verify_review.

  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 gives explicit guidance: 'Only call this on the user's explicit request to post — never speculatively.' It also tells the agent to first get line numbers from mr_diff_lines, naming the prerequisite sibling tool and explaining how lines_filter maps source lines to diff positions.

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

• mr_review_contextA
  5/5.0
  Behavior5/5

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

  The description fully discloses behavior: it extracts top-N identifiers, always runs dependency_impact, and optionally enriches if the repo was indexed. It explicitly states the semantic layer is additive and that a result with semantic_available=false is complete and actionable. It also discloses the warning condition for root not checked out and how to resolve it. With no annotations, the description carries the full transparency burden and excels.

  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 well-structured: a concise summary sentence, a bulleted process list, a clean Args section, and a Returns section. Every sentence adds value—no filler. It is appropriately sized for the tool's complexity and front-loads the core purpose.

  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 lack of annotations and output schema, the description is remarkably complete. It covers the input parameters, the processing logic, dependencies on index_repo, the return format (including error/warning fields), and even setup guidance. No gaps are apparent for an agent to select and invoke the tool correctly.

  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%, so the description must compensate, and it does. It explains each parameter: url (Full GitLab merge request URL), root (Absolute path to local repository clone), max_symbols (Maximum changed symbols to analyze, default 8). This adds meaning beyond the bare 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 tool's specific function: 'Graph-first review context: dependency impact per changed symbol, plus optional semantic enrichment.' It uses a specific verb ('runs dependency_impact') and resource (MR diff symbols), and distinguishes from siblings by positioning it as a single-call alternative to running dependency_impact per symbol.

  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?

  Explicitly says when to use it: 'Use this as a single-call alternative to running dependency_impact separately for each changed symbol.' Also provides a precondition (requires root checked out to MR) and a remedy ('set it up with myopic worktree' and re-run). This is clear guidance on when and how to use the tool.

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