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

With no annotations, the description carries the transparency burden. It states the tool only formats and is not a lookup, and it discloses a payment detail. For a zero-parameter formatting tool, this is adequate behavioral context; it does not hide destructive or network-effecting behavior.

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 short clauses, front-loaded with the core purpose and example. The final payment note is tangential to tool function but small and not confusing; no redundant 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?

For a no-parameter, no-output-schema formatting tool, this is nearly complete: it tells what the tool produces, shows the output format, and narrows scope. The only gap is that it never expicitly states the return value is a string, though the example makes that obvious.

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 declares zero formal parameters, so the description is the only source of meaning. It explains the composition ('greffe city + SIREN/SIRET') and provides an example, which is useful even though the schema does not formalize inputs.

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?

Description names a specific deliverable—a French RCS invoice mention—gives a concrete example, and states the operation is formatting only. It explicitly distinguishes itself from a Kbis lookup, which separates it from sibling tools like check_siret or rm_mention.

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 'Format only, not a Kbis lookup' gives a clear when-not-to-use boundary and implies when it should be used: generating a formatted RCS mention for an invoice. It does not name a specific alternative tool, but the context and exclusions are clear enough.

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