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

With no annotations provided, the description carries the full burden; it does disclose that the call is free and that output is Markdown, which are genuine behavioral facts. However, it omits error behavior (unknown SIREN), and whether any auth or rate limit applies.

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 short fragments with zero filler, and the most decision-relevant fact ('Free') is front-loaded. It is perhaps over-compressed — a few more words on failure mode would not have hurt — but nothing is wasted.

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?

No output schema exists, and the description does partially compensate by naming the return format (full fiche as Markdown). Against a no-annotation, no-output-schema tool it still lacks error/edge-case behavior, leaving the agent with gaps.

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% and the single parameter is documented with a pattern and description in the schema. 'By SIREN' in the description merely restates the schema, adding no new semantic detail, so 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?

The description states the resource ('company fiche'), the return format ('full fiche as Markdown'), and the key ('by SIREN'), which is a clear verb+resource+key combination. It implicitly distinguishes itself from search_companies (which would find a SIREN) but never names that sibling explicitly.

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 only guidance is 'Free', which tells the agent there is no cost but says nothing about when to prefer this over search_companies or get_document, nor what happens with an unknown SIREN. The agent must infer that a SIREN is already known.

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