search_companies

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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuine non-obvious behavior beyond them: company-officer personal data is intentionally excluded from results, which prevents an agent from expecting it. It omits other behaviors such as the default exclusion of ceased companies (active_only=true).

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, zero filler, and the core capability is front-loaded. The return-field enumeration is partly redundant given an output schema exists, costing it a point.

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 an output schema present, the description need not (and mostly does not need to) explain return values, and the privacy note plus coverage scope make it callable. Minor gap: it never discloses that ceased companies are excluded by default via active_only=true, a default that could surprise an agent.

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 all four parameters (query, limit, active_only, postal_code) are already documented in the schema. The description adds no syntax, format or defaults beyond what the schema provides; the mention of name/address/SIREN/SIRET merely restates the query field. Baseline 3 is appropriate.

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 (Search) and resource (French companies, associations and public bodies), plus the searchable axes (name, address, SIREN/SIRET). The verb "search" inherently separates it from get_company, but the description never names or contrasts the sibling tools, so it stops short of the top band.

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?

Usage is only implied: the query accepts a name, address words or an identifier, so an agent can infer it is for discovery when you have partial input. It gives no when-to-use vs get_company (single-record lookup) and no exclusions, so an agent must derive the routing itself.

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