Server Quality Checklist

Tool Scores

• get_wine_pairingsA
  4.3/5.0
  Behavior4/5

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

  Annotations already mark this as read-only and idempotent, so the description does not need to repeat that. It adds useful behavior beyond the schema: the id/page mutually exclusive modes, the site's wording scale from 'Bon accord' to 'Accord parfait', and the alphabetical ordering that maps dishes to pages.

  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 front-loaded with the primary action and is compact overall. The final explanatory clause about alphabetical ordering is slightly redundant with 'alphabetical index' but earns its place by helping an agent reason about page selection.

  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?

  With an output schema present and annotations covering the read-only/idempotent profile, the description provides the missing behavioral context: dual id/page modes and the nature of the returned pairings. It does not specify what happens if both or neither parameter is supplied, but that is a minor gap given the surrounding structure.

  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?

  The schema already describes both parameters with 100% coverage, so the baseline is 3. The description adds extra meaning by explaining that 'id' is the number in a dish's address and that 'page' reads the alphabetical index, reinforcing how the two parameters relate to the tool's behavior.

  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 action ('Read the wines Supertoinette ranks for one dish') and identifies the exact resource and the id routing. It clearly distinguishes this tool from the recipe-oriented siblings by focusing on wine pairings, so an agent can select it without opening the schema.

  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 gives clear guidance on when to use 'id' versus 'page' and explains where dish identifiers come from in the alphabetical index. It does not explicitly name sibling alternatives or state when not to use this tool, but the context is clear enough.

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

• scale_ingredientsA
  4.5/5.0
  Behavior5/5

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

  Beyond the readOnly and idempotent annotations, the description explains per-line outcomes ('scaled', 'rounded', 'unscaled'), states that no unit-system conversion occurs, and notes that approximate measures like a pincée retain their own size. This is meaningful behavioral disclosure.

  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: purpose and mode first, then return behavior, then boundary constraints. Every sentence adds useful information without repetition or fluff.

  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 complete schema coverage, meaningful annotations, an output schema, and the description covers key edge behavior such as unscaled lines and approximate measures. An agent has enough to invoke it correctly and interpret results.

  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 every parameter. The description reinforces the either factor or from_servings/to_servings relationship and clarifies 'together', but it does not add substantial new parameter-level meaning 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 states a specific verb and resource: it rescales a list of French ingredient lines, offline. It clearly distinguishes this transformation tool from the sibling recipe lookup tools by emphasizing the computational and offline nature.

  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 gives clear context for when to use the tool: rescaling ingredient lines offline, with either a factor or serving-count conversion. It does not explicitly name alternatives or exclusion conditions, but the purpose is sufficiently distinct from the sibling tools.

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

• search_recipesA
  4.5/5.0
  Behavior5/5

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

  Annotations already declare read-only, open-world, and idempotent behavior, and the description adds valuable non-obvious details: no total_available, last_page semantics, facets, and the fact that an unknown category behaves like an empty match while the answer says so. This is exactly the kind of site-specific behavior an agent 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 main action is front-loaded, and every sentence earns its place by explaining a behavior or boundary the agent would otherwise have to discover at runtime. The density is high 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?

  For a 4-parameter search tool with an output schema and safety annotations, the description covers all operational edge cases: no site total, last_page, facets, invalid-category behavior, and the get_recipe handoff. Nothing needed for a correct call 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%, and every parameter already has detailed meaning (page limits, the 39-row ceiling, French query, exact category spelling). The description echoes some of this but does not materially add beyond the schema, so the baseline 3 is appropriate.

  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 action and resource: search Supertoinette by a dish or an ingredient, and links results to get_recipe via the identifier. This clearly distinguishes the tool from siblings like browse_recipes or list_categories, so an agent knows exactly what it does.

  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 gives clear context: search by dish/ingredient, narrow with a facet-derived category, then read via get_recipe. It does not explicitly list conditions against sibling tools like browse_recipes or list_categories, so it stops short of full exclusions; that is the only gap.

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

• browse_recipesA
  4.7/5.0
  Behavior5/5

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

  Beyond the readOnly/idempotent annotations, the description reveals real behaviors: the site publishes no total, so last_page is the only listing-length indicator; rows expose difficulty, total time, and the identifier get_recipe consumes; and categories are tied to a system-provided source. This gives an agent useful expectations that annotations alone do not.

  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?

  Four sentences, each earning its place: purpose, category sourcing rule, row contents, and pagination behavior. The core action is front-loaded and the description is compact without losing necessary context.

  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?

  With a 100%-described schema, an output schema, and annotations covering read-only/idempotent behavior, the description fills the remaining operational gaps: how categories are chosen, what rows look like, and how pagination terminates. Nothing an agent needs to call it correctly 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?

  The schema already documents all three parameters well, so the baseline is 3. The description adds value by warning that categories are 'never assembled by hand' and clarifying what returned rows contain, though most parameter-level detail remains in 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?

  States a specific action and resource: read the recipes of one Supertoinette category, page by page. It clearly differentiates from siblings by explaining that each row carries the identifier get_recipe reads, and the title contrasts category browsing with list_categories, search_recipes, and get_recipe.

  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 gives strong operational guidance: the category must come from list_categories or a recipe's tags and must never be hand-assembled. It does not explicitly state when not to use this tool or name the alternative for cross-category search, so it stops short of a 5.

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

• list_categoriesA
  4.7/5.0
  Behavior5/5

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

  Annotations already mark the tool read-only, idempotent, and non-destructive; the description adds valuable behavior beyond that: entries carry browse_recipes tokens, 'listed_in' reflects site placement, malformed tokens yield pages the site does not hold, and the list is not exhaustive. This is rich, relevant behavioral disclosure with no contradiction.

  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 opens with a crisp purpose statement, then each subsequent sentence adds essential information: token usage, placement semantics, the warning against hand-built tokens, and coverage limitations. There is no filler 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?

  With an output schema present and annotations covering the safety profile, the description supplies the missing piece: what the entries mean, how to use them with browse_recipes, and how far the categories list extends. An agent has everything needed to invoke and interpret the tool 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?

  The tool has zero parameters, so the baseline is 4 as per the rubric. The input schema is empty and fully described by its 100% coverage, and the description correctly focuses on output semantics rather than inventing parameter guidance.

  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 ('List') and a clear resource ('categories Supertoinette browses its recipes by'), immediately distinguishing it from sibling tools like get_recipe or search_recipes. It also names browse_recipes as the downstream consumer of the returned tokens, further clarifying its role.

  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 gives clear context: use this tool to obtain category tokens for browse_recipes, and warns not to hand-construct tokens. It also notes the tool's coverage limitation—tag-based categories are not included—but it does not explicitly name an alternative tool for those cases, leaving some routing to inference.

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

• get_recipeA
  5/5.0
  Behavior5/5

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

  Beyond the annotations (read-only, idempotent, non-destructive), the description discloses what fields are returned, that unpublished times come back as null rather than zero, and how rescaling reports whether quantities landed exactly or were adjusted to measurable amounts. This is valuable behavioral context that annotations alone do not provide.

  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 front-load the core purpose, then layer an example, return contents, null semantics, and optional rescaling behavior without any filler. Every sentence earns its place and the structure is highly scannable.

  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 simple two-parameter schema, the rich annotations, and the presence of an output schema, the description covers everything an agent needs to select and invoke the tool correctly. It explains the identifier, the return shape, missing-data behavior, and the optional parameter's effect.

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

  Parameters5/5

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

  Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning: it illustrates the id format with a concrete URL example and explains the behavioral effect of servings on output, including the distinction between exact arithmetic and kitchen-measurable rounding. This goes well beyond the schema's short parameter 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 specifies a concrete verb ('Read'), a specific resource ('one recipe on Supertoinette'), and the exact addressing scheme ('the number in its address'). It is clearly distinct from the sibling search/browse/list tools because it retrieves a single recipe by identifier rather than discovering or enumerating recipes.

  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 establishes that this tool is for reading a recipe already identified by its numeric address, and the schema's id guidance adds 'Search for a dish when you do not have one,' pointing the agent to search_recipes when the identifier is unknown. The servings behavior is also explained with enough context to know when to use the optional parameter.

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