Server Quality Checklist

Tool Scores

• list_profilesA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. 'Lists' conveys a read-only operation, and the 'optionally checking' phrase hints at an extra verification step, but it does not disclose that verify says it fetches from an external URL (as in the schema) or that it might be slow. No contradictions.

  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?

  A single sentence with no wasted words. The core purpose is front-loaded, and the optional behavior is appended without distracting from the main operation.

  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 simple two-optional-parameter listing tool, the description covers scope and optional behavior. It does not describe the return format, but for a list operation this is likely inferable; overall, nothing critical 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%, with both 'verify' and 'category' having clear descriptions. The tool description adds no parameter-specific meaning beyond the schema, so the baseline 3 applies.

  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 uses a specific verb ('Lists') and a clear resource ('BRouter routing profiles') with a scope qualifier ('known to this server'), distinguishing it from sibling tools like plan_route and compare_profiles. The optional availability check adds clarity without ambiguity.

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

  Usage Guidelines3/5

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

  The description implies use when you need to discover server-known profiles, but it does not explicitly contrast with sibling tools or state when to use it instead of get_profile_options. No exclusions or preconditions are mentioned, so guidance is only implied.

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

• compare_profilesA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden. It explains that the tool computes routes for multiple profiles and reports comparison metrics, which is useful. It does not disclose side effects, error behavior, or constraints such as profile availability, though for a routing comparison the main behavior is well covered.

  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?

  A single sentence that front-loads the action (routes same waypoints with several profiles) and the purpose (compare metrics to pick best style), with no filler or repeated schema 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?

  For a tool with nested parameters and no output schema, the description names all key output dimensions and states the input structure. Optional parameters are left to a detailed schema, and available profiles can be discovered from sibling list_profiles, so an agent has enough context to invoke it 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 coverage is 75% and most parameters already have descriptive text, so the baseline is 3. The description adds an example profile list and links profiles to the comparison metrics, but does not materially add meaning to waypoints, avoid_areas, or profile_options beyond the schema.

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

  Purpose5/5

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

  The description uses a specific verb ('routes', 'compares') and a clear resource (waypoints across multiple routing profiles), and names concrete comparison metrics (distance, riding time, climb, surface mix). This distinguishes it from siblings like plan_route or list_profiles by emphasizing multi-profile comparison rather than single-route planning or profile enumeration.

  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?

  It clearly frames the use case: pick a route style by comparing the same waypoints under several profiles. It does not explicitly name alternatives or state when not to use it, but the 'several profiles' contrast makes the selection condition reasonably clear.

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

• geocode_placeA
  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 for behavioral disclosure. It states the read-only nature ('looks up') and the main output ('coordinates'), but it does not disclose that multiple candidates may be returned, that results may be ambiguous, or how the response is structured. This is adequate for a simple lookup but lacks richer 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 a single, efficient sentence with no filler. The core action ('looks up coordinates') is front-loaded, followed by the object and use case. Every word earns its place.

  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 simple, read-only geocoding tool with no output schema, the description is nearly complete: it states the input scope, the output concept, and the routing use case. It does not specify the response format, but the title and description together make the tool's purpose and behavior sufficiently clear for correct 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?

  Schema description coverage is 100%, so the baseline is 3. The description adds minimal semantic value by clarifying that 'query' can be a place name, address, or POI, but it does not add significant explanation for limit, language, near_lat, or near_lon beyond what the schema already documents.

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

  Purpose5/5

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

  The description states a specific verb ('looks up'), a clear resource ('coordinates for a place name, address or POI'), and a concrete use case ('as a routing waypoint'). It distinguishes itself from sibling tools like plan_route or compare_profiles, which serve different purposes.

  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 by tying the tool's output to routing waypoints, implying it should be used whenever a place needs to be converted to coordinates before route planning. It does not explicitly exclude alternatives or mention when not to use it, but no sibling tool performs geocoding, so the usage context is reasonably clear.

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

• plan_routeA
  4/5.0
  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 discloses the return payload (distance, climb, time, surfaces, turn instructions, shareable link), optional file saving, coordinate/place-name waypoints, and the large-GeoJSON caveat. It does not mention failure modes, rate limits, or network dependency, but the core behavioral surface is well covered.

  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?

  Three sentences cover the core action, output payload, waypoint flexibility, and optional saving behavior with no filler. Important details are front-loaded in the first sentence, and the later sentences add only necessary nuance.

  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 a complex schema with 12 parameters and no output schema, the description effectively summarizes what the tool returns and the key modes of use. It names most salient behaviors but leaves some output structure details (e.g., exact JSON shape, units) implicit; still, the description is sufficient for an agent to understand what the tool does and when it is appropriate.

  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 coverage is 100%, so the schema already documents all 12 parameters and their meanings. The description adds a helpful high-level characterization of waypoints (coordinates or place names) and optional GPX/GeoJSON/KML export, but this overlaps with existing parameter descriptions rather than substantially extending them.

  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 names a specific verb ('Plans a cycling route'), a specific engine (BRouter), and a detailed list of outputs, which makes the tool's purpose unmistakable. It clearly differentiates from its siblings (profile comparison, geocoding, profile listing/options) without needing to mention them.

  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 the tool is for routing through waypoints and references list_profiles/get_profile_options for related configuration, but it never explicitly states when to use plan_route versus an alternative or when not to use it. The context is clear enough from the purpose, but no direct usage-selection guidance is provided.

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

• get_profile_optionsA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of explaining behavior. It discloses that the tool reads a profile's source and extracts tunable options, and the examples convey that the output is a list of parameter names. It doesn't explicitly state read-only semantics, but 'fetches' strongly implies a non-mutating operation, and no side effects are suggested.

  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 sentence that front-loads the core action and result, then quickly gives examples and a usage note. Every phrase adds value, and there is no wasted wording.

  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 one parameter and no output schema, the description explains what it does, what it returns, and how to use the result. The absence of error-handling details or return format specifics is minor given the simplicity of the operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already provides 100% coverage for the single parameter 'profile' with a description and example values. The tool description adds context about the parameter's role (used to fetch that profile's source), but this is largely implied by the purpose and doesn't provide additional semantic depth beyond the schema.

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

  Purpose5/5

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

  The description clearly states a specific action ('fetches a profile's source') and its result ('lists the parameters it exposes'), with concrete examples of the parameters. It distinguishes itself from siblings like plan_route and compare_profiles by focusing on retrieving tuning options rather than routing or comparison.

  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 tells the agent to pass the fetched parameters to plan_route via profile_options, making the tool's role in a workflow clear. It doesn't explicitly exclude alternatives or mention when not to use it, but the connection to plan_route provides strong contextual guidance.

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