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

With no annotations, the description carries the full burden and does well: it discloses that the document itself is never transmitted, that only the fingerprint enters a public registry, and that the returned receipt is immutable proof of existence at a date. It omits auth requirements, cost, and duplicate-hash behavior, so not quite exhaustive.

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 tight sentences that front-load the action and then the guarantee and return value. Every clause earns its place with no repetition of the title or schema.

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 two-parameter tool with no output schema, the description covers the essential contract: what is registered, what is not sent, and what comes back (a receipt proving dated existence). Details like verification steps or error cases are absent but not critical here.

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%, with both sha256 and libelle fully documented in the schema, so baseline is 3. The description adds only a light semantic point ('le document n'est jamais envoyé', i.e. the hash is the payload), which doesn't meaningfully extend the parameter documentation.

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: registering the SHA-256 fingerprint of a document the user keeps. The phrase 'd'un document que l'utilisateur garde' implicitly separates it from dater_url (which would act on a URL rather than a local file), but no sibling is named 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 description implies the right context (you hold the document, only the hash is registered), but never states when to pick this over dater_url, chercher_empreinte, or lire_recu, nor any preconditions such as having computed the hash first.

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