Server Quality Checklist

Tool Scores

• search_locationsB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description must fully disclose behavior, but it only states what the tool resolves. It does not disclose that the response likely contains multiple possible location matches, how results are ordered, or how pagination behaves. The agent cannot anticipate the reply structure before invoking the tool.

  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, tightly worded sentence that front-loads the tool's purpose, accepted inputs, and output. There is no repetitive fluff, and the sentence earns its place.

  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?

  The tool has no output schema and no annotations, so the description should clarify result shape and usage context. It omits that the response is likely a list of candidates, how to choose between them, or how pagination works, leaving unclear behavior for an agent trying to invoke and interpret the result.

  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 description adds real semantic detail for the query parameter by listing accepted input forms (city, place, postal, IATA, ICAO) beyond the schema's generic 'Location search text'. However, page and limit are undocumented in the schema and the description does not compensate for those, so the parameter semantics are only partially 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 uses a specific verb ('Resolve') and resource, and clearly enumerates accepted inputs (city, place, postal code, IATA code, ICAO code) and outputs (coordinates and elevation). This makes the tool's scope unmistakable and it is clearly distinct from the forecast-based sibling tools.

  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 that this tool is the location-lookup step before forecast retrieval, but it does not explicitly say when to use it versus the get_forecast siblings or when not to use it. An agent can infer the use case from the context, but the guidance is not explicit.

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

• get_forecast_imageA
  3.5/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It does usefully disclose that the response is a PNG and that access depends on the API key's meteoblue entitlement. However, it does not mention error conditions, how invalid locations are handled, or any other side effects or restrictions.

  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 brief, direct, and front-loaded: a clear generation statement, the input style, the exact output format, and the access caveat. No sparse or irrelevant content is present.

  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 8 parameters, no annotations, and no output schema, the description covers the essential purpose and output but misses important contextual detail: how the type/options parameters interact, whether coordinate and location inputs are mutually exclusive, and when to prefer this tool over get_forecast. It is sufficient to start, but not fully complete for an agent navigating the full tool landscape.

  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 description adds a small amount of parameter meaning by saying the image can be generated by place name or coordinates, which maps to location or latitude/longitude. The schema already covers those semantics well, and the description does not explain the type enum, options object, language, countryCode, or elevation parameters, which remain somewhat ambiguous despite partial schema descriptions.

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

  Purpose5/5

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

  The description clearly identifies the operation: generate a meteoblue forecast meteogram by place name or coordinates, and explicitly states the output is a PNG. This distinguishes the tool from siblings like get_forecast and search_locations, 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 Guidelines2/5

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

  The description gives no guidance on when to use this tool over get_forecast or search_locations. It does not state whether this is the image counterpart to get_forecast, when to use it with coordinates, or whether search_locations should be called first. Only the very purpose implies an image deliverable.

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

• get_forecastA
  3.8/5.0
  Behavior3/5

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

  Since no annotations are given, the description carries the full burden. It discloses that place names are resolved internally and that only packages documented for the Free Weather API are accepted, but it omits rate limits, authentication expectations, potential errors, and the structure of the returned forecast JSON.

  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 short, focused sentences: the first states core purpose, the second clarifies place-name behavior, and the third restricts acceptable package inputs. There is no filler or repetition.

  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?

  This is a 13-parameter tool with no annotations and no output schema, yet the description only covers the location and free-package constraints. It leaves important operational details—such as what package names mean, how forecastDays/historyDays interact, and what the resulting forecast JSON looks like—entirely implicit, making it hard for an agent to call correctly for varied user requests.

  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 low (38%). The description contributes some meaning by framing place name and coordinates as alternative input modes, and it adds a constraint about acceptable packages. However, it does not compensate for the many undocumented parameters like historyDays, forecastDays, or the unit parameters, which are left to the schema's enum/default values only.

  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 specifies a verb and resource ('Get meteoblue forecast JSON'), the output format (JSON), and the two main input modes. The word 'JSON' also immediately separates it from the image-returning sibling get_forecast_image.

  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 indicates that place names can be passed directly and are resolved via the Location Search API, which tells an agent it does not need a separate lookup first. The mention of JSON implies this is for raw data, not images, though the description does not explicitly name an alternative for those cases.

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