Server Quality Checklist

Tool Scores

• get_relevant_contextB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions returning 'minimal, targeted code snippets' but doesn't specify what 'relevant' means, how relevance is determined, whether it accesses cached data, or any performance characteristics like rate limits or permissions needed. This leaves significant gaps for a tool that presumably queries codebases.

  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 a single, efficient sentence that front-loads the core purpose. It avoids unnecessary words, though it could be slightly more structured by separating purpose from behavioral traits. Every part earns its place, but it's borderline minimal.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the complexity of code context retrieval, no annotations, and no output schema, the description is incomplete. It doesn't explain what 'relevant' entails, how snippets are selected or formatted, error conditions, or dependencies on other tools like 'index_repository.' For a tool with 2 parameters and likely non-trivial behavior, this is inadequate.

  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%, so the schema already documents both parameters fully. The description adds no additional meaning beyond what the schema provides—it doesn't clarify how 'query' should be formulated or what 'maxTokens' impacts in practice. Baseline 3 is appropriate as the schema does the heavy lifting.

  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 states the tool's purpose: 'Get code context relevant to a natural language query' with the specific action 'Returns minimal, targeted code snippets.' It distinguishes from siblings like 'search_code' by focusing on contextual relevance rather than broad searching, though it doesn't explicitly name alternatives.

  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 for natural language queries about code context, but provides no explicit guidance on when to use this tool versus siblings like 'find_similar' or 'search_code.' It lacks any mention of prerequisites, exclusions, or specific scenarios where this tool is preferred.

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

• find_similarB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool is 'useful for discovering' purposes, but it doesn't disclose key behavioral traits like whether it's read-only or destructive, authentication needs, rate limits, or how similarity is determined (e.g., based on code structure or semantics). This leaves significant gaps for an AI agent to understand the tool's behavior.

  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 appropriately sized and front-loaded, consisting of two concise sentences. The first sentence states the purpose clearly, and the second adds useful context without redundancy. Every sentence earns its place, making it efficient and well-structured.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has no annotations and no output schema, the description is somewhat complete but lacks details on behavioral traits and return values. It covers the purpose and usage context adequately for a simple tool, but for a code analysis tool with potential complexity, it should do more to explain how results are returned or what 'similar' means, making it minimally viable.

  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 has 100% description coverage, with clear descriptions for both parameters ('symbolName' and 'limit'). The description adds no additional meaning beyond what the schema provides, such as explaining what a 'symbol' entails or how 'similar' is defined. Since the schema does the heavy lifting, the baseline score of 3 is appropriate.

  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 states the tool's purpose: 'Find code similar to a given symbol.' It specifies the verb ('Find') and resource ('code similar to a given symbol'), making the function understandable. However, it doesn't explicitly differentiate from sibling tools like 'find_symbol' or 'search_code', which might have overlapping purposes, preventing a perfect score.

  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 provides implied usage guidelines by stating it's 'Useful for discovering related implementations, similar patterns, or alternative approaches.' This gives context on when to use it, but it doesn't explicitly mention when not to use it or name alternatives among sibling tools, such as how it differs from 'find_symbol' or 'search_code'.

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

• get_dependenciesB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool 'finds' dependencies, implying a read-only operation, but doesn't specify if it's cached, requires specific permissions, has rate limits, or what the output format looks like. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

  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 front-loaded, with two sentences that efficiently convey the purpose and utility. Every word earns its place, avoiding redundancy or fluff, making it easy for an agent to parse quickly.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the basic purpose and usage hint but lacks details on behavioral traits, output format, or error handling. With no annotations to fill gaps, the description should do more to be fully helpful for an agent.

  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 has 100% description coverage, with clear documentation for 'filePath' and 'symbol.' The description adds minimal value beyond the schema, only implying that 'symbol' is optional and for tracing dependencies. Since the schema already covers parameters well, the baseline score of 3 is appropriate, as the description doesn't significantly enhance parameter understanding.

  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 states the tool's purpose: 'Find all dependencies (imports/requires) for a file or symbol.' It specifies the verb ('Find') and resource ('dependencies'), and distinguishes it from siblings like 'find_symbol' or 'get_file_summary' by focusing on dependency analysis. However, it doesn't explicitly differentiate from all siblings (e.g., 'get_repository_structure' might also involve dependencies), so it's not a perfect 5.

  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 provides implied usage guidance with 'Useful for understanding what code needs,' suggesting it's for code analysis contexts. It doesn't explicitly state when to use this tool versus alternatives like 'find_similar' or 'search_code,' nor does it mention prerequisites or exclusions. The guidance is helpful but not comprehensive.

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

• clear_cacheA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the tool's purpose and when to use it, but doesn't disclose important behavioral traits like whether this operation requires specific permissions, whether it's destructive to data (beyond cache), what happens during execution (e.g., temporary unavailability), or any rate limits. The description adds value but leaves significant gaps.

  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 perfectly concise with two sentences that each earn their place. The first states the core action, the second provides usage context. No wasted words, well-structured, and front-loaded with the primary purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's moderate complexity (cache clearing operation with one parameter) and no annotations or output schema, the description provides adequate but incomplete coverage. It explains what the tool does and when to use it, but lacks details about behavioral implications, error conditions, or what happens after execution. For a tool that likely affects system state, more context would be helpful.

  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%, so the schema already fully documents the single 'path' parameter. The description doesn't add any parameter-specific information beyond what the schema provides (e.g., it doesn't explain path format requirements or cache location details). Baseline 3 is appropriate when the schema does all the parameter documentation work.

  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 states the action ('Clear') and target ('cached index for a repository'), providing a specific verb+resource combination. It distinguishes from siblings like 'index_repository' by focusing on cache removal rather than creation. However, it doesn't explicitly differentiate from all possible cache-related operations that might exist in other contexts.

  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 this tool ('if cache becomes corrupted or you want to force a fresh index'), giving practical scenarios. It doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools, though 'index_repository' is implied as a follow-up action.

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

• get_usage_statsA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool does (view usage stats with a comparison) and hints at a reset capability via the parameter, but doesn't cover other behavioral aspects like whether it requires specific permissions, how data is presented, or if it has rate limits. It adds some value but lacks comprehensive 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 two sentences with zero waste: the first sentence states the purpose and scope, and the second provides usage guidance. It's front-loaded with the core functionality and efficiently conveys essential information without 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?

  Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is mostly complete. It explains the purpose and usage context well. However, without an output schema, it doesn't describe return values (e.g., format of statistics), which is a minor gap for a monitoring tool. It compensates somewhat by specifying the comparison aspect.

  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%, so the schema already documents the single parameter ('reset') with its type and default. The description doesn't add any parameter-specific details beyond what's in the schema, such as explaining the implications of resetting or how it affects future usage tracking. Baseline 3 is appropriate when the schema handles parameter documentation.

  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 specific verb ('View') and resource ('token usage statistics for this session'), with precise scope ('how many tokens each MCP tool used vs what full file reads would have cost'). It distinguishes from siblings by focusing on usage metrics rather than code analysis, repository operations, or caching.

  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 this tool ('to verify token savings'), which implies it's for monitoring and validation purposes. However, it doesn't explicitly state when not to use it or name alternatives among siblings, leaving some ambiguity about its exclusive role.

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

• find_symbolA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: fuzzy matching for typos, performance ('much faster'), accuracy ('better accuracy'), and output format ('returns exact file path and line number'). It doesn't mention error handling, rate limits, or authentication needs, but covers core operational traits well.

  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 highly concise and front-loaded: the first sentence states the core purpose and key alternative, followed by supporting details. Every sentence earns its place by adding critical information (fuzzy matching, output, performance), with zero wasted words.

  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?

  Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is nearly complete. It covers purpose, usage, key behaviors, and output, but lacks details on error cases or response structure. With no output schema, it could better explain return values, but it's sufficient for effective use.

  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%, so the schema already documents both parameters thoroughly. The description adds no specific parameter semantics beyond implying 'symbol' is for 'functions, classes, or variables' and 'type' filtering, which the schema's enum already covers. This meets the baseline for high schema coverage.

  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 with specific verbs ('find', 'returns') and resources ('symbols', 'functions, classes, or variables'), explicitly distinguishing it from sibling tool 'Grep' (likely referring to 'search_code'). It specifies the exact output ('file path and line number') and key features ('fuzzy matching', 'faster', 'better accuracy').

  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 usage guidance: 'PREFERRED FOR SYMBOLS: Use this INSTEAD OF Grep when looking for specific functions, classes, or variables.' It clearly states when to use this tool (for symbols) and when not to (use Grep/search_code for other cases), naming the alternative tool directly.

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

• get_classA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it's a read operation ('Get'), offers optional filtering, and highlights efficiency gains ('Saves 80%+ tokens'). However, it doesn't mention potential limitations like error handling or performance constraints, leaving some gaps.

  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 highly concise and front-loaded, with every sentence earning its place. It starts with a key benefit ('PREFERRED OVER Read'), explains the tool's function, quantifies efficiency, and ends with usage guidance—all in three efficient sentences with zero waste.

  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?

  Given the tool's moderate complexity (3 parameters, no output schema, no annotations), the description is largely complete. It covers purpose, usage, and benefits well. However, without an output schema, it doesn't explain return values (e.g., format of class definitions), which is a minor gap in context.

  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%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by implying filtering capabilities ('Optionally filter specific methods') but doesn't provide additional syntax or format details. Baseline 3 is appropriate when the schema does the heavy lifting.

  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 with specific verbs ('Get class definition', 'filter specific methods') and resources ('class structure', 'class methods'). It distinguishes from siblings by explicitly mentioning 'PREFERRED OVER Read' and contrasting with reading entire files, making its scope unambiguous.

  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 guidance on when to use this tool ('when you need class structure or specific class methods') and when not to use it (vs. reading full files). It names an alternative ('Read') and quantifies the benefit ('Saves 80%+ tokens'), giving clear context for selection among siblings.

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

• get_file_summaryA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it's a read-only operation (implied by 'get'), it provides structured metadata rather than full content, and it offers efficiency benefits ('saves 90% tokens'). However, it doesn't mention potential limitations like file size constraints or supported file types.

  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 extremely concise and front-loaded, with every sentence earning its place. The first sentence establishes purpose and value, the second provides usage guidance, and the third quantifies efficiency benefits. There's zero wasted text.

  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?

  Given the tool's moderate complexity (single parameter, no output schema, no annotations), the description provides excellent context about what the tool does and when to use it. It effectively compensates for the lack of annotations and output schema by clearly explaining the tool's behavior and value proposition. The only minor gap is not specifying what exactly 'file structure' includes beyond the listed elements.

  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 description coverage, the input schema already fully documents the single parameter. The description doesn't add any parameter-specific information beyond what's in the schema, so it meets the baseline score of 3 for adequate coverage when the schema does the heavy lifting.

  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 with specific verbs ('get file structure') and resources ('exports, functions, classes, imports'), and explicitly distinguishes it from sibling tools by naming 'Read' as an alternative. It provides concrete value ('without reading full content', 'saves 90% tokens').

  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 guidance on when to use this tool ('PREFERRED FOR FILE OVERVIEW', 'when you need to understand what's in a file without seeing implementation details') and when not to use it ('INSTEAD OF Read'). It clearly positions this tool against a specific alternative in the context.

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

• get_functionA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool retrieves function code (read operation implied), emphasizes efficiency ('Saves 85% tokens'), and specifies the return format ('Returns only the function definition with signature'). However, it lacks details on error handling, performance limits, or authentication needs, leaving some behavioral aspects uncovered.

  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 highly concise and well-structured: three sentences with zero waste. The first sentence states the purpose and key benefit, the second provides usage context, and the third clarifies the return value. Each sentence adds essential information, and the use of emojis and bold phrasing enhances readability without verbosity.

  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?

  Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description is largely complete. It covers purpose, usage guidelines, behavioral traits, and return format. However, without an output schema, it could benefit from more detail on response structure or error cases, and the lack of annotations means some operational context (e.g., idempotency) 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%, providing baseline documentation for both parameters. The description adds minimal parameter semantics beyond the schema—it implies 'functionName' is required for retrieval and 'filePath' is optional for targeting, but doesn't elaborate on format, constraints, or interaction effects. This meets the baseline for high schema coverage without significant added value.

  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: 'Get complete function code without reading the entire file.' It specifies the verb ('Get'), resource ('function code'), and distinguishes it from sibling tools like 'Read' (implied) and 'get_file_summary' by focusing on specific function extraction. The mention of token savings further clarifies its specialized 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?

  The description provides explicit usage guidance: '⭐ PREFERRED OVER Read' indicates a clear alternative, 'Use when you need a specific function implementation instead of reading full files' defines the optimal context, and 'Saves 85% tokens compared to Read' quantifies the benefit. This directly addresses when to use this tool versus alternatives like reading entire files.

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

• get_repository_structureA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it's a read-only operation (implied by 'Get'), returns structure without file contents, and is optimized for 'clean' output. However, it doesn't mention potential limitations like error handling, performance characteristics, or output format details, leaving some gaps in behavioral understanding.

  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 extremely concise and well-structured in just two sentences. Every word earns its place: the first sentence states purpose and key differentiators, the second provides usage guidance and limitations. It's front-loaded with the most important information ('PREFERRED OVER ls/tree') and wastes no space on redundant information.

  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?

  Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description provides good contextual coverage. It clearly explains what the tool does, when to use it, and what it doesn't do. However, without an output schema, the description doesn't specify what the structure output looks like (e.g., tree format, JSON, etc.), leaving some ambiguity about the return value.

  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%, so the schema already documents both parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. It mentions 'specific subdirectory to analyze' and 'depth' implicitly through context but provides no additional syntax, format, or usage details for parameters.

  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: 'Get clean repository structure showing directories and file types.' It specifies the verb ('Get'), resource ('repository structure'), and scope ('directories and file types'), and explicitly distinguishes it from sibling tools by stating it's 'PREFERRED OVER ls/tree' and should be used 'INSTEAD OF running ls, tree, or Glob.'

  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 guidance on when to use this tool versus alternatives: 'Use this INSTEAD OF running ls, tree, or Glob for understanding project layout.' It also clarifies the tool's limitations: 'No file contents, just structure,' which helps define appropriate use cases. This directly addresses when to choose this tool over other methods.

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

• index_repositoryA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it's a required first step for enabling other tools, uses caching for efficiency, is fast (<2s for most repos), and can be forced to re-index. It doesn't cover error conditions or permissions, but for a tool with no annotations, this is strong coverage of operational behavior.

  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 highly concise and front-loaded, with every sentence earning its place: it states the purpose, caching behavior, usage guidelines, and performance. No wasted words, and the emoji adds visual emphasis without distraction.

  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?

  Given the tool's complexity (a prerequisite indexing operation with caching), no annotations, and no output schema, the description does well by covering purpose, usage, caching, and performance. It could mention error handling or output format, but for a tool with 100% schema coverage and clear behavioral context, it's largely complete.

  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%, so the schema already documents both parameters fully. The description doesn't add any parameter-specific details beyond what the schema provides (e.g., it doesn't explain 'path' or 'forceReindex' further). Baseline 3 is appropriate when the schema does the heavy lifting.

  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 specific action ('index or re-index'), the target resource ('the repository'), and the purpose ('to enable all context-manager tools'). It distinguishes this tool from siblings by emphasizing it as a required first step for repository work, unlike other tools that perform specific queries or analyses.

  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 guidance on when to use this tool: 'when starting work on a repository or if files have changed significantly.' It also specifies when not to use it by noting it 'uses cached index if files haven't changed,' implying it's unnecessary without changes. While it doesn't name specific alternatives, it positions this as a prerequisite for other tools.

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

• search_codeA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a search operation (implied read-only), returns ranked results with minimal context, and supports regex. However, it doesn't mention potential limitations like performance, file size constraints, or authentication needs, leaving some gaps for a tool with no 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 highly concise and well-structured: three sentences with zero waste. The first sentence states purpose and key features, the second compares to Grep, and the third specifies use cases. Every sentence earns its place by adding distinct value.

  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?

  Given no annotations and no output schema, the description does a good job covering core functionality and usage context. However, it lacks details on return format (beyond 'ranked results with minimal context') and doesn't address potential errors or edge cases. For a search tool with 3 parameters, it's mostly complete but could benefit from more behavioral context.

  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%, so the schema already documents all parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema—it doesn't explain regex syntax, glob pattern details, or result ranking criteria. Baseline 3 is appropriate when the schema does the heavy lifting.

  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 with specific verbs ('search for code patterns with regex support') and resources ('code patterns'), and explicitly distinguishes it from the sibling tool 'Grep' by highlighting advantages like ranking by relevance and AI-optimized output. This makes it easy to understand what the tool does and how it differs from alternatives.

  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 guidance on when to use this tool versus alternatives: it states '⭐ PREFERRED OVER Grep' and explains why ('Better than Grep because it ranks by relevance and provides AI-optimized output'), and specifies use cases ('Use for pattern matching and text search'). This gives clear context for selection among sibling tools.

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