Server Quality Checklist

Tool Scores

• nanostores_runtime_overviewA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe, repeatable read operation. The description adds valuable context about what the tool returns (health check data types) and mentions the 'compact' parameter's purpose for 'lower token cost,' which isn't covered by annotations. No contradiction with annotations exists.

  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 efficiently structured in two sentences: the first states the purpose and return data, the second provides parameter examples. Every sentence adds value without redundancy, and it's appropriately front-loaded with the core functionality.

  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 (diagnostic read operation), rich annotations (readOnlyHint, idempotentHint), and the presence of an output schema, the description is reasonably complete. It covers the tool's purpose and key return aspects, though it could benefit from more explicit differentiation from sibling tools to fully guide usage.

  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 fully documents both parameters (windowMs, compact). The description adds minimal value by providing example parameter structures ({}, {windowMs: 60000, compact: true}) and noting the compact parameter reduces token cost, but doesn't explain parameter interactions or default behaviors beyond what the schema provides.

  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 as providing a 'high-level health check of the running app's state management' and lists specific return data (active stores, error-prone stores, unused stores, activity patterns). It distinguishes from some siblings like 'nanostores_ping' (basic connectivity) but doesn't explicitly differentiate from similar diagnostic tools like 'nanostores_store_summary' or 'nanostores_runtime_coverage'.

  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 some guidance with 'Use this when you want a high-level health check' and gives parameter examples, but it doesn't explicitly state when to choose this tool over similar siblings (e.g., 'nanostores_store_summary' or 'nanostores_runtime_coverage'). The context is implied rather than explicitly contrasted with alternatives.

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

• nanostores_runtime_coverageA
  4.3/5.0
  Behavior4/5

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

  Annotations indicate read-only and idempotent operations, which the description aligns with by implying analysis without mutation. The description adds valuable context about the tool's purpose (comparing static and runtime data) and timing ('after running the app'), which annotations do not cover, though it lacks details on rate limits or specific output 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 front-loaded with the core purpose, followed by usage guidance and an example, all in two efficient sentences with no redundant information, making it highly concise and well-structured.

  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 (comparing static and runtime data), the presence of annotations (readOnlyHint, idempotentHint) and an output schema, the description adequately explains the tool's purpose and usage context without needing to detail return values or behavioral traits already covered elsewhere.

  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 parameter 'projectRoot' is fully documented in the schema. The description adds minimal extra context with an example but does not provide significant additional meaning beyond what the schema already specifies.

  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 ('compare', 'find') and resources ('static analysis graph', 'runtime event data'), distinguishing it from siblings by focusing on coverage verification rather than scanning, searching, or analyzing stores directly.

  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 ('Use after running the app to verify instrumentation completeness'), but it does not explicitly state when not to use it or name specific alternatives among the sibling tools for different scenarios.

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

• nanostores_clear_cacheA
  4.4/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds valuable context about the tool's purpose (clearing cached index to enable fresh scans) and when to use it, which complements the annotations. However, it doesn't mention potential side effects like temporary performance impact during re-scanning.

  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?

  Two sentences with zero waste. The first sentence provides usage context, the second explains the action and consequence. Every word serves a purpose, and the information is front-loaded with the primary use case.

  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 tool with comprehensive annotations and no output schema, the description provides excellent context about when and why to use it. It could slightly improve by mentioning what 'clears the cached project index' entails operationally, but overall it's highly complete for this tool's complexity level.

  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% with the parameter well-documented. The description doesn't add any parameter-specific information beyond what's in the schema, which already explains the optional rootUri parameter and its behavior when omitted. This meets the baseline expectation 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 verb ('clears') and resource ('cached project index'), specifying it's for the project analysis cache. It distinguishes from siblings by explicitly mentioning nanostores_scan_project as the complementary operation that will perform a fresh scan after cache clearance.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: 'when scan results seem stale or after making file changes that the server may not have detected.' It also specifies the alternative action (nanostores_scan_project) that should follow, creating clear operational sequencing.

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

• nanostores_pingA
  4.4/5.0
  Behavior4/5

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

  Annotations indicate readOnlyHint=true, idempotentHint=true, and openWorldHint=false, covering safety and idempotency. The description adds value by specifying the diagnostic context (verifying aliveness and logger bridge connectivity), which isn't captured in annotations. It doesn't contradict annotations and provides useful behavioral context beyond them, though it could mention expected output or error conditions.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that directly states the usage context. It's front-loaded with clear intent, has no redundant information, and every word earns its place. Perfectly concise for a simple diagnostic tool.

  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 low complexity (simple ping with one optional parameter), rich annotations (readOnly, idempotent, closed-world), and the presence of an output schema (which handles return values), the description is complete enough. It clearly states the diagnostic purpose without needing to explain parameters or behavioral details already covered elsewhere.

  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?

  There is 1 parameter with 0% schema description coverage (no description in schema). The tool description doesn't mention parameters at all, but since there are 0 required parameters and a default is provided in the schema, the baseline is high. The description compensates by clearly stating the tool's purpose, making parameter details less critical for this simple ping tool.

  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 as verifying server aliveness and checking logger bridge connectivity, which is specific (verb+resource). However, it doesn't distinguish this from potential sibling tools that might also test connectivity or provide health checks, though none are explicitly listed among siblings. The purpose is unambiguous but lacks sibling differentiation.

  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 states when to use this tool: 'when you need to verify the MCP server is alive or check whether the runtime logger bridge is connected.' This provides clear context for usage without alternatives needed, as it's a diagnostic tool with a specific, narrow purpose. No misleading or vague guidance is present.

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

• nanostores_docs_searchA
  4.5/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe, repeatable read operation. The description adds valuable context about what gets searched (guides, API references, best practices) and the relationship to other resources (nanostores://docs/page/{id}), which goes beyond what annotations provide. It doesn't mention rate limits or authentication needs, but with good annotation coverage, this is sufficient.

  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 efficiently structured with zero waste: it starts with the core purpose, explains parameter usage with clear examples, and provides an alternative for related functionality. Every sentence earns its place by adding practical guidance. The example format is particularly helpful without being verbose.

  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 moderate complexity, rich annotations (readOnlyHint, idempotentHint), 100% schema coverage, and the presence of an output schema, the description is complete enough. It covers the purpose, usage guidelines, parameter interactions, and relationship to other resources without needing to explain return values (handled by output schema) or repeat what annotations already declare.

  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 documents all four parameters thoroughly. The description adds some semantic context about how parameters interact (query required unless storeKind provided, combining both for targeted search) and provides concrete examples, but doesn't add significant meaning beyond what's in the schema descriptions. The baseline of 3 is appropriate when schema does most of the work.

  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', 'Search') and resources ('Nanostores documentation', 'guides, API references, and best practices'). It distinguishes this search tool from siblings like nanostores_clear_cache or nanostores_store_summary by focusing on documentation retrieval rather than runtime operations or analysis.

  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 specifies to use nanostores://docs/page/{id} for reading full page content after finding relevant pages. It also explains how to combine parameters effectively with clear examples, making it easy to understand appropriate usage scenarios.

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

• nanostores_find_noisy_storesA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe, repeatable read operation. The description adds valuable context beyond annotations by explaining that it returns stores 'ranked by activity' based on 'frequent changes, many action calls,' which clarifies the behavioral output and purpose, though it doesn't mention rate limits or authentication needs.

  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 the core purpose and usage guidelines in the first sentence, followed by a concise example. Every sentence earns its place by providing essential information without redundancy, making it highly efficient and well-structured.

  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 (diagnostic analysis), rich annotations (readOnlyHint, idempotentHint), and the presence of an output schema, the description is complete enough. It clearly explains the tool's role in performance investigation, distinguishes it from siblings, and provides usage examples, covering all necessary context without needing to detail return values (handled by output schema).

  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 fully documents the parameters (limit, windowMs, compact). The description provides example usage with {limit: 10} and {windowMs: 30000, compact: true}, which adds practical context but doesn't add semantic meaning beyond what the schema already specifies. This meets the baseline of 3 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', 'pinpoint') and resources ('stores ranked by activity'), explicitly mentioning 'frequent changes, many action calls' to distinguish it from sibling tools like nanostores_store_activity or nanostores_store_summary which might focus on different aspects of store behavior.

  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 investigating performance issues or excessive re-renders.' It also distinguishes it from alternatives by specifying it returns stores 'ranked by activity' to 'pinpoint bottlenecks,' helping differentiate from other sibling tools that might serve different diagnostic purposes.

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

• nanostores_project_outlineA
  4.5/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond what annotations provide. While annotations indicate read-only, idempotent, and closed-world behavior, the description reveals that this tool returns 'a compact summary instead of full store/subscriber lists' and uses 'same scan data, smaller response.' This provides important implementation details about response size and data source that aren't captured in 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 perfectly concise and well-structured. Two sentences efficiently convey the tool's purpose, what it returns, when to use it, and when to use the alternative. Every word serves a clear purpose with no redundancy 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?

  Given the tool's moderate complexity, comprehensive annotations (readOnlyHint, idempotentHint, openWorldHint), and the presence of an output schema, the description provides complete contextual information. It explains the tool's purpose, differentiates it from alternatives, and describes the response format, which is sufficient since the output schema will handle return value details.

  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 and only one optional parameter, the schema already fully documents the 'projectRoot' parameter. The description doesn't add any additional parameter semantics beyond what's in the schema, so it meets the baseline expectation but doesn't provide extra value in this dimension.

  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: providing a 'quick overview of Nanostores usage in the project' with specific content elements (store kind distribution, top directories, hub stores ranked by connectivity). It explicitly distinguishes this from its sibling 'nanostores_scan_project' which provides complete lists, making the distinction 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 versus alternatives: 'Use this for a quick overview...' and 'Use nanostores_scan_project when you need the complete list of stores and relations.' This clearly defines the use case context and names the specific alternative tool for different needs.

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

• nanostores_store_activityA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe, repeatable read operations. The description adds valuable context beyond this by specifying the return content ('recent events, change frequency, action calls, and errors'), debugging use cases, and optional storeName behavior, though it doesn't mention rate limits or auth needs, which keeps it from 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 front-loaded with the core purpose, followed by usage guidance and examples, all in three concise sentences with zero wasted words. Each sentence adds specific value, making it efficient and well-structured for quick comprehension.

  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 debugging complexity, rich annotations (readOnlyHint, idempotentHint), 100% schema coverage, and the presence of an output schema, the description is complete enough. It covers purpose, usage, behavioral context, and examples, leaving no critical gaps for an agent to invoke the tool effectively.

  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 fully documents all 6 parameters. The description adds minimal parameter semantics beyond the schema, such as implying storeName's optionality and providing example usage, but doesn't explain parameter interactions or deeper meanings, aligning with 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 ('debugging a specific store's runtime behavior') and resources ('store runtime activity'), distinguishing it from siblings like nanostores_find_noisy_stores or nanostores_store_summary by focusing on detailed event-level debugging rather than high-level summaries or noise detection.

  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 debugging a specific store's runtime behavior — why it updates too often, what actions trigger changes, or whether it emits errors'), includes an alternative usage pattern ('Omit storeName to get activity across all stores'), and offers concrete examples, making it clear how to apply it in different scenarios.

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

• nanostores_store_impactA
  4.5/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond what annotations provide. While annotations indicate read-only and idempotent operations, the description explains that this tool returns 'the full ordered downstream chain in a single response' and clarifies how subscribers are included ('Subscribers appear at the same hop as the store they react to'). This provides important implementation details not captured in 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 efficiently structured with zero wasted sentences. It begins with the primary use case, explains the return format, provides sibling tool differentiation, and includes a concrete example - all in four tightly focused sentences that each serve a distinct 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 tool's complexity and the presence of both comprehensive annotations and an output schema, the description provides complete contextual information. It explains the tool's purpose, when to use it versus alternatives, the structure of the response, and includes a practical example - covering all necessary aspects for effective tool selection and invocation.

  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 documents all three parameters thoroughly. The description doesn't add significant parameter semantics beyond what's in the schema, though it does provide an example using the 'name' parameter. This meets the baseline expectation when schema coverage is complete.

  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: 'trace what recomputes if X changes' and 'Returns the full ordered downstream chain in a single response.' It specifically distinguishes this tool from sibling tools like nanostores_store_summary and nanostores_store_subgraph, providing explicit differentiation.

  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 ('call this once — not nanostores_store_summary on each downstream store') and when to use an alternative ('Use nanostores_store_subgraph instead when you also need upstream ancestors'). It also includes a practical example to illustrate proper usage.

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

• nanostores_store_subgraphA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false. The description adds valuable behavioral context beyond these annotations: it explains the BFS algorithm with configurable radius, provides a practical starting point (radius=1), warns about performance implications on highly connected hub stores, and gives concrete usage examples. No contradictions with annotations exist.

  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 efficiently structured with zero wasted sentences. It opens with clear usage differentiation, states the core purpose, explains key behavioral aspects (radius usage and hub store considerations), and provides concrete examples. Every sentence adds value and is appropriately front-loaded with the most important guidance.

  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 that annotations cover safety properties (read-only, idempotent), schema coverage is 100%, and an output schema exists (so return values don't need explanation), the description provides excellent contextual completeness. It addresses when to use the tool, behavioral nuances, practical usage tips, and examples - exactly what's needed beyond the structured data.

  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 all four parameters. The description adds some semantic context about the radius parameter (recommending starting with radius=1 and explaining when to increase it), but doesn't provide additional meaning for storeId, name, or projectRoot beyond what's in their schema descriptions. This meets the baseline expectation when schema coverage is complete.

  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: to get both upstream sources AND downstream dependents together (the store subgraph) using BFS within a configurable radius. It specifically distinguishes this from the sibling tool nanostores_store_impact, which provides only the downstream causal chain. The verb 'get' combined with the resource 'store subgraph' is specific and well-differentiated.

  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 directly states: 'If your question is "what recomputes downstream when X changes?", use nanostores_store_impact instead' and 'Use this tool only when you need both directions: upstream sources AND downstream dependents together.' This includes clear when-not-to-use criteria and names the alternative tool.

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

• nanostores_store_summaryA
  4.5/5.0
  Behavior4/5

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

  The annotations already provide readOnlyHint=true, idempotentHint=true, and openWorldHint=false, which cover safety and idempotency. The description adds valuable context about what information is returned (kind, file location, direct subscribers, first-level derived relations) and provides a concrete example of parameter usage, which enhances understanding beyond 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 efficiently structured with three sentences: the first states the purpose and scope, the second provides usage guidance and alternative, and the third gives a concrete example. Every sentence adds value with zero wasted words, making it easy to parse and understand.

  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 that annotations cover safety and idempotency, schema coverage is 100%, and an output schema exists, the description provides complete contextual information. It explains what the tool returns, when to use it, and provides an example, making it fully adequate for an agent to understand and invoke this tool correctly.

  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 all parameters. The description adds some semantic context by explaining that it accepts 'store id or name' and providing an example, but doesn't add significant meaning beyond what's in the schema. This meets the baseline of 3 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: to provide details about a specific store including its kind, file location, direct subscribers, and first-level derived relations. It uses specific verbs ('summarize') and resources ('store'), and distinguishes itself from the sibling tool nanostores_store_subgraph by specifying it's for single-level details rather than multi-hop dependency chains.

  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 when you need details about a specific store' and 'For multi-hop dependency chains use nanostores_store_subgraph instead.' It clearly defines the context and provides a named alternative for different use cases.

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

• nanostores_scan_projectA
  4.7/5.0
  Behavior4/5

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

  Annotations indicate read-only and idempotent operations, which the description does not contradict. The description adds valuable context beyond annotations by explaining caching behavior ('bypass cache' with force parameter) and output variations (compact vs. full modes), enhancing the agent's understanding of how the tool behaves in different scenarios.

  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 the core purpose, followed by concise usage guidelines and examples. Every sentence adds value—no redundancy or filler—making it efficient for quick comprehension by an AI agent while maintaining clarity.

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

  Completeness5/5

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

  Given the tool's moderate complexity, rich annotations (readOnlyHint, idempotentHint), and the presence of an output schema, the description is complete. It covers purpose, usage scenarios, and parameter nuances without needing to detail return values, providing all necessary context for effective tool selection and invocation.

  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?

  With 67% schema description coverage, the description compensates by providing practical semantics: it explains when to use compact mode ('for a token-efficient directory-level overview') and force parameter ('to bypass cache'), adding meaning beyond the schema's basic descriptions. However, it does not address rootUri, leaving a minor gap in parameter context.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the specific action ('Returns the complete store/subscriber/relation index') and resource ('for the project'), distinguishing it from siblings like nanostores_project_outline or nanostores_runtime_overview by focusing on indexing rather than outlining or runtime analysis. It explicitly mentions what is returned, making the purpose 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 compact mode ('for a token-efficient directory-level overview') versus full mode ('when you need to iterate over every entity or build a complete picture'), and includes an example for context. It clearly differentiates use cases, helping the agent choose appropriately without needing to infer from sibling tools.

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