What's Cooking

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the description only needs to add operational context. It adds that results are short picks, that limit defaults to 5 and maxes at 20, and that query matches titles, tags, and ingredients. Return fields and pagination behavior are still not specified.

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

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

The description is compact and front-loads the core purpose before listing optional inputs and the get_explore_recipe follow-up. The example is useful, though the initial question is slightly less direct than a plain declarative sentence.

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

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

With no output schema and three optional parameters, the description covers all inputs, default/max limit behavior, and the path to full recipe details via get_explore_recipe. It does not specify the fields in the short picks returned, but it gives enough context to invoke the tool correctly.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds useful meaning beyond the schema: query is matched against titles, tags, and ingredients, and author is illustrated with "Gusto". The limit default and max are already in the schema.

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

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

The description clearly states that this tool browses recipes shared by people and Gusto on What's Cooking, and it explicitly contrasts the result with get_explore_recipe. It does not distinguish its purpose from whats_for_dinner, so it stops short of full sibling differentiation.

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

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

It explicitly says to call get_explore_recipe with an id when the full recipe is needed, which gives clear routing guidance for the closest sibling. It does not state when to use this tool versus whats_for_dinner or any cases where this tool should be avoided.

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

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

Annotations already declare a safe, read-only, idempotent lookup, and the description adds useful behavioral detail: servings is optional and quantities are scaled when it differs from the original. It does not cover error behavior or return format, but with annotations present this is solid additional context.

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

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

The purpose is front-loaded as a direct question, followed by compact input notes and a concrete example. Every element is useful and there is no filler.

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

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

For a simple two-parameter read-only lookup with annotations and full schema coverage, the description gives enough to invoke it correctly, including id provenance and servings scaling. Return-shape details are not required because there is no output schema, though error/not-found behavior is not addressed.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description still adds value by explicitly marking id as required, noting servings as optional, and clarifying that scaling happens conditionally when servings differs from the original, plus giving an example call.

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

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

States a clear retrieval action and resource: the full recipe for an Explore pick, using an id sourced from browse_explore. It is distinguishable from browse_explore as a follow-up lookup, though it does not explicitly discuss its other sibling.

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

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

The description makes the usage context clear by saying the id comes from browse_explore and by presenting this as the way to get the full recipe for that pick. It does not spell out exclusions or when to prefer another tool, so it stops short of full when/when-not guidance.

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

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

It discloses the return contents, optional inputs, defaults, and kitchen assumptions such as salt/pepper/oil/water being on hand. The annotations already cover safety hints, and the description adds useful behavioral context, though it does not explain any state persistence despite readOnlyHint=false.

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

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

The description is front-loaded with purpose and output, then compactly covers inputs, assumptions, repeat behavior, and an example. It is dense but every sentence adds useful information.

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

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

Given seven optional parameters, no output schema, and annotations that cover safety, the description is complete enough: it explains what is returned and how the main inputs behave. An agent has sufficient information to invoke it correctly.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds useful semantics: all inputs are optional, servings default/max, diet as hard constraints, and assumed pantry staples. It also provides an example invocation.

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

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

The description states a specific verb and resource: Gusto decides one complete dinner and returns the recipe, steps, and shopping list. It is clear what the tool does, but it does not explicitly distinguish itself from the sibling browse/recipe tools.

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

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

It gives a clear usage context ("What should I cook tonight with what I have?") and says to call again with different inputs for another idea. It does not explicitly state when not to use it or name the alternative siblings.

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