Server Quality Checklist

Tool Scores

• list_filtersA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond these: the site accepts arbitrary facet values and returns zero for unknown ones (guessed spellings look like confident absence), and that the listed values are only an excerpt. No contradiction with annotations.

  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 moderately long but every sentence carries information: purpose, parameter usage, open-world behavior, and excerpt limitation. It is front-loaded with the primary purpose and structured logically, though slightly 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 has an output schema (so return format is defined elsewhere), one optional parameter, and the description covers purpose, usage, behavioral nuances, and parameter semantics, nothing essential is missing for an agent to invoke it correctly.

  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?

  Schema coverage is 100% because the 'query' parameter has a description in the schema. The tool description goes further by explaining the semantic impact of passing vs. not passing the query (counts within a search vs. whole listing), which adds meaning beyond the schema's basic description.

  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 ('List'), a resource ('axes a recipe search can be narrowed along'), and the context (BBC Good Food), with counts. It is clearly distinct from the sibling search_recipes, which searches recipes rather than listing filter facets.

  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 explains when to pass the 'query' parameter (to measure counts within a search) versus omitting it (whole listing), and advises reading this before narrowing a search. It does not explicitly name the alternative tool or state when not to use it, but the context is sufficient.

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

• search_recipesA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive, so safety is covered. The description adds non-obvious behavioral quirks: unknown filter values yield a count of zero, and unmatched terms return identical rows instead of an empty list. It also notes that exclude_premium removes rows after the page arrives, shortening it, which is nuanced beyond 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 compact yet dense with value: purpose, narrowing options, prerequisite call, behavioral caveats, and result structure. It is front-loaded with the purpose and each sentence earns its place. No fluff or repetition.

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

  Completeness5/5

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

  The tool has an output schema (present) and comprehensive annotations. The description covers how to use the filters, what to expect in terms of ranking and counts, and notes the behavioral nuance of exclude_premium affecting page length. It also references the sibling tool appropriately. Nothing essential for correct invocation is missing.

  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?

  Schema description coverage is 100%, so each parameter has a baseline description. The tool description adds meaningful context on how several parameters (diet, cuisine, meal_type, difficulty) depend on list_filters and warns about the zero-count behavior. It doesn't repeat schema details but provides usage-level semantics that elevate beyond the baseline 3.

  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 immediately states the verb and resource: 'Search recipes on BBC Good Food and return a listing.' It is specific about the domain (BBC Good Food) and the output (a listing). It differentiates from the only sibling, list_filters, by implying this tool returns actual recipe rows, not filter metadata.

  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 instructs to 'call list_filters first for the values each one takes', providing clear when-to-use guidance. It also clarifies that the site ranks rather than filters, warning the agent to read titles rather than trust counts, which is essential for correct interpretation of results.

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