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 immutability ('seal ... immutable on-chain proof'), re-validation before anchoring ('re-checks everything'), an authorization requirement, and the returned artifacts. It stops short of stating cost/gas implications or what happens on a repeat call against the same id, which are the remaining behavioral gaps for an irreversible on-chain write.

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 tight sentences, front-loaded with what the tool does, then the precondition, then the auth requirement and return values. Every sentence carries information the agent needs; nothing is restated from the schema or name.

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 mutation tool with no annotations and no output schema, the description covers purpose, precondition, authorization and return artifacts, which is enough to call it correctly. The nested 'donnees' object's shape and any failure/idempotency behavior remain unspecified, keeping it just short of fully complete.

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 id, donnees and agent (including the crucial 'Same data object that passed tracea_check_demarche' note). The description adds no parameter-level detail such as format or coupling of 'donnees' to the previous check, so it sits at the baseline.

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 ('Seal a validated file as an immutable on-chain proof') with the chain context (Tracea Online, Base). It also names the sibling it depends on (tracea_check_demarche) and the artifact it returns, so an agent can distinguish it from tracea_signature or tracea_demarche_preuve immediately.

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 precondition: 'Call this ONLY after tracea_check_demarche returned ok:true', which is both a when-to-use rule and an exclusion. It adds a second gating condition — 'Requires the caller to be an authorized harness' — so the agent knows whether it is even eligible to invoke this tool.

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