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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the safety profile is covered; the description still adds substantial non-obvious context: no quality ranking, no price or availability guarantees, website-level extraction is not a verified qualification, and unknown dates stay unknown. It also tells the agent which fields to cite (citation_url, evidence.source_url) and that visit_url is merely an optional navigation link.

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?

Front-loaded with the core action, then prerequisites, then constraints — a sensible information hierarchy. It is dense with operational rules and nearly every sentence earns its place, though the quoting/citation sentence is slightly compressed and mixes output guidance into the search description.

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 return-value explanation is not required, and the description instead adds sourcing and limitation caveats that the schema cannot express. The remaining gap is pagination and faceted-parameter behavior (limit/cursor, how sector vs service interact) for an 8-parameter, zero-required 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 only 25% — only q and city are documented structurally — so the description carries real weight here. It reinforces q's limitation and points to get_taxonomies for valid category values (sector, service, language, software), but it never explains limit, cursor pagination, or what each faceted parameter accepts or how they combine. Useful compensation, but incomplete for a low-coverage 8-parameter 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?

States a specific verb and resource ('Search French accounting firms') plus the crucial scope qualifier 'by exact AND filters', which tells an agent this is a structured filter lookup rather than a free-text search. That qualifier alone distinguishes it from the sibling find_accountants and from get_cabinet's single-record lookup.

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 routes the agent to prerequisites: resolve_city for ambiguous locations and get_taxonomies for exact category values. It also gives a negative boundary ('q is a firm name or SIREN, never a service query') and a behavioral rule for the zero-result case ('do not remove a filter or widen the city without agreement'), which is exactly the guidance an agent needs to invoke this correctly.

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