Search foods in TACO

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

Annotations only declare readOnlyHint=true, and the description is consistent while adding real behavioral context: accent-insensitivity, typo tolerance, regional-name aliasing (aipim, macaxeira, mandioquinha), and the form of the returned identifiers. The dataset's known gaps are disclosed, though nothing is said about ordering or relevance behavior.

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?

Three sentences, front-loaded with the corpus and language, then retrieval behavior, then the handoff to get_nutrients. Every clause contributes information an agent needs.

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?

An output schema exists, so no return-value exposition is needed, and the description still identifies the key return artifact (ids) and the corpus's language and unit basis. Enough context is present for correct invocation and correct interpretation of results.

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 both query and limit are already documented in the schema. The description reinforces the Portuguese-name constraint and enumerates regional synonyms, but adds no syntax or format detail beyond what the schema states; baseline 3 applies.

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 specific verb and resource ('Find foods in the Brazilian TACO table') plus scope detail (597 items, per 100 g, Portuguese names) that separates it from get_nutrients and calc_meal. An agent knows exactly what corpus this searches and in what language.

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?

Names the downstream tool explicitly ('Returns ids to use with get_nutrients') and gives a coverage caveat ('Restaurant dishes and brands are mostly absent') that tells the agent when this lookup will fail. It stops short of naming an alternative to use instead when coverage is missing, so usage is clear but exclusions aren't fully routed.

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