Search recipes

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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds key behavioral details: the no-pagination rule, the reason (robots.txt), and the return of ids/URLs for get_recipe. This is valuable context not present in annotations.

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 a single well-structured paragraph, front-loaded with the purpose and examples. Every sentence contributes value—no fluff, and the pagination caveat is efficiently explained.

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?

The tool's complexity is well covered: external site specifics, language guidance, pagination restrictions, and integration with get_recipe. With an output schema present, the description doesn't need to explain return structure, but it covers all necessary usage context.

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 description coverage is 100%, so baseline is 3. The description adds practical semantics: it clarifies that limit applies to a single page and that pagination is unavailable, which supplements the schema's parameter descriptions. Examples for query enrich understanding.

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 the tool searches Marmiton for recipes by free text (dish, ingredient, or both) with concrete examples. It distinguishes from sibling get_recipe by noting it returns the id and URL needed to read a recipe with get_recipe.

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 gives explicit usage context: French terms work best, one call returns one page, and pagination is disallowed due to robots.txt. It advises narrowing the query instead of asking for more pages, providing clear when-and-how guidance.

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