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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description only adds the 'Newest first' ordering guarantee; it says nothing about data freshness, upstream gazette lag, or what happens when a company has no announcements. With annotations carrying the main burden, this is adequate but thin.

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?

Two compact clauses, front-loaded with the resource and its coverage, ending with the ordering guarantee. Every phrase earns its place and there is no filler.

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 documentation is not needed, and the description adequately conveys scope and ordering for a simple filtered read. A brief note on volume, freshness, or empty results would close the remaining gap.

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% — limit, siren and category all carry their own descriptions, including the category enum values. The description adds no format, defaulting, or filtering nuance beyond the schema, so the 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?

Names a specific resource (BODACC legal announcements for a company) and enumerates its contents: insolvency judgments, deregistration, accounts filings, changes, sales. This is unmistakably distinct from the sibling tools search_companies and get_company, so an agent can select it without opening the schema.

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 never states when to reach for this tool versus the company siblings, or any precondition beyond the implicit need for a company identifier. There are no exclusions or alternative-routing hints, so usage must be inferred entirely from the resource name.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety and idempotency profile is fully covered without the description. The description adds only the scope of data returned, with no mention of behavior for unknown SIRENs, rate limits, or data freshness (e.g. 'latest published' revenue).

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?

A single front-loaded sentence that leads with the resource and scope before enumerating fields; there is no filler. The field list is somewhat long, but every item conveys what the caller receives.

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 one fully documented required parameter, a rich output schema, and annotations covering the safety profile, the definition supplies nearly everything an agent needs to call it correctly. The only gap is the absence of guidance on when to prefer it over its siblings.

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% and the single 'siren' parameter already documents the 9-digit SIREN / 14-digit SIRET format with spaces allowed. The description adds no parameter meaning at all, so the baseline 3 for schema-complete parameters 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?

The description gives a specific verb-like resource ('Full public profile of one French company') and enumerates the content returned (identity, status, head office, VAT, revenue, net income, labels), which clearly separates it from a list/search tool. It does not, however, name or explicitly contrast with the sibling search_companies or get_bodacc_announcements, so it falls short of a 5.

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 phrase 'one French company' implies this is a single-entity detail lookup rather than a discovery search, which suggests when to use it over search_companies. But there is no explicit when/when-not guidance, no mention of prerequisites, and no routing to the sibling tools for other needs.

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

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.