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

Annotations already mark the tool as read-only, open-world, and idempotent. The description adds substantial behavioral context beyond those: it describes the outcome when search is omitted (a small reference list, except for NOVA and Nutri-Score which are returned complete), the ID format patterns ('en:' prefix vs. bare digits/letters for NOVA and Nutri-Score), and the fact that category tags are often plural. This goes well beyond the annotation hints and informs the agent about the tool's return characteristics and pitfalls.

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 efficient and front-loaded: the first sentence captures the core purpose. Subsequent sentences add specific, non-redundant details—each covers a distinct aspect (facet coverage, ID formats, pluralization, and the search-omission behavior). No sentence is filler; the length is justified by the necessary context. It remains structured enough for an agent to parse quickly.

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 description is comprehensive for an agent to call this tool correctly. It explains the purpose, the parameter semantics, the expected output (as input to off_search_products), and the edge cases (pluralization, format differences). It even covers the closed vs. open vocabulary distinction for facets. With schema coverage at 100% and an output schema present, the description fills all the gaps an agent would need for correct invocation and integration with the sibling tool.

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. The description adds meaningful value over the schema: it explains the ID format conventions (e.g., 'en:organic', 'en:kombuchas'), the pluralization caveat, and that NOVA groups return digits '1'-'4' while Nutri-Score returns letters 'a'-'e'. It also clarifies that 'limit' is capped and there is no paging, which is already in the schema but reinforced. This enriches parameter understanding beyond the schema alone.

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 opens with a specific verb and resource: 'Resolve a human term to the canonical Open Food Facts tag ID that off_search_products filters on.' This clearly distinguishes it from sibling tools like off_search_products (which filters) and off_get_product (which retrieves a product), by stating its role as a resolver/translator for taxonomy tags. It also enumerates the covered facets, leaving no ambiguity about scope.

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?

Explicitly states when to use: to resolve terms before filtering via off_search_products. It provides conditional guidance: omitting search returns a small reference list, and it warns about the pluralization pitfall ('use the returned id rather than constructing one'). It also tells the agent to pass IDs exactly as returned, guiding the workflow. No alternatives are listed, but the sibling connection is clear, and the conditional behavior of the search parameter is well described.

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