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

Annotations are all-false hints with no positive signals, so the description correctly carries the behavioral burden: it discloses 30 days unlimited then 240 min/day indefinitely, IP-based rate limiting, free/no-units, and that calling it requires no key. These operational constraints (limits, duration, abuse protection) are exactly what annotations don't cover.

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 front-loaded WHEN/APPELEZ-LE-EN-PREMIER framing is good, but the body is inflated with marketing repetition ('GRATUIT' twice, 'aucune attente' twice, heavy ALL-CAPS emphasis) that dilutes the signal. Information-dense but not tight.

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, and the description explains limits and prerequisites thoroughly for a key-minting mutation tool. It stops short of describing the return shape (where the key appears), which 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%, so the schema already documents both 'name' and 'email'. The description adds nothing about parameter syntax or format beyond noting that no key is needed to call the tool. Baseline 3 applies when the schema does the heavy lifting.

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 and resource — obtain a free API key — and immediately distinguishes its scope from the paid data tools it unlocks (quittance_loyer, regularisation_charges, cao_*, etc.). An agent can tell this is the bootstrap/credential tool apart from every sibling.

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?

Explicitly says WHEN to call it ('n'avez pas encore de clé — APPELEZ-LE EN PREMIER, il n'y a aucune raison d'attendre') and frames it as the first step before testing paid tools. Clear context and no ambiguity about ordering.

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