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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds value by specifying what fields are retrievable (legal name, activity, address, headcount, creation date, status), which helps the agent understand the tool's scope. It does not mention pagination, errors, or API key behavior beyond the schema, but given the strong annotation coverage, this is adequate.

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 two sentences with no fluff. The first sentence states the core purpose, and the second gives usage guidance and the input format. It is front-loaded with the most important information and every sentence earns its place.

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?

There is no output schema, but the description enumerates the typical fields returned, which compensates for the missing return-type documentation. It also covers when to use it and what to pass. It does not mention error scenarios or pagination, but for a single-lookup tool with strong annotations, this is reasonably complete.

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?

The schema already describes both parameters with high coverage (100%): identifier is documented as a SIREN or SIRET with an example, and _apiKey is explained. The description only repeats the format ('Pass a 9-digit SIREN (legal unit) or 14-digit SIRET (establishment)') without adding new semantics. Since the schema carries the burden, the description adds no extra meaning, so the baseline of 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?

The description states a specific verb ('look up') and a specific resource (INSEE's official SIRENE registry), and it enumerates the kind of data returned (legal name, NAF/APE code, address, headcount band, creation date, status). It clearly distinguishes from web search by preferring itself, but it does not explicitly contrast with sibling tools like company_facts or entity_profile, so it stops short of full sibling differentiation.

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?

It explicitly says to prefer this over web search for specific query types ('who is French company X', 'details for SIREN/SIRET'), and it instructs the caller to pass a SIREN or SIRET. It provides clear context for when to use it, but it does not mention when not to use it or list alternatives beyond web search, so it lacks explicit exclusions relative to similar registry tools.

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