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

With no annotations, the description carries the full burden and handles it well: it discloses the external-registry cross-check behavior (network/validation dependency beyond local schema checks) and the exact return contract ({ ok: true, recordHash } vs { ok: false, errors }). It stops short of stating idempotency, rate limits, or whether any state is persisted.

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?

Front-loaded with the core purpose, then return shape, then the imperative sequencing rule – each sentence earns its place. The bolded caps ('THE', 'ALWAYS') are emphatic but not wasteful, though they push slightly toward verbosity.

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?

Despite having no output schema, the description inlines both success and failure response shapes, names the external validation dependency, and states the required call ordering. Nothing essential for invoking the tool correctly is missing.

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 both parameters (id, donnees) are documented in the schema, so the baseline is 3. The description only reinforces that donnees fields must match tracea_demarche_schema, adding no format or constraint detail beyond the structured field docs.

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+resource ('check' / validate submitted démarche data) and adds the distinguishing mechanism: validation against the official procedure schema plus cross-checking critical values against French registries (SIRET/INSEE Sirene). This clearly separates it from siblings like tracea_anchor_demarche and tracea_demarche_preuve.

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?

Explicit sequencing guidance: 'ALWAYS call this BEFORE telling the user the file is ready' and 'fix the exact fields reported' tells the agent exactly when to invoke it and what to do after. It also points to tracea_demarche_schema as the source of field names, but does not state explicit exclusions or when NOT to call it.

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