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

Beyond the readOnlyHint annotation, the description explains the precise behavioral contract: reports are triage hypotheses, do not modify law, never affect other tools' responses, and do not change 'non dérivé' to 'dérivé'. It also discloses that the entry goes to the server log, which clarifies the nature of the side effect.

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 description is three sentences and front-loads the definition of a report before the behavioral consequences and parameter notes. It is dense but every sentence carries substantive information, though the first sentence is a long enumeration.

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 report tool with annotations but no output schema, the description covers purpose, behavioral boundaries, address requirements, and log destination. It does not describe what the caller receives in response, which is a minor gap given the lack of output schema.

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%, so the schema already documents all parameters. The description still adds value by stating that the address is required and verified against the catalog, and by grouping package, fragment and/or predicate as address components; callId is tied to X-Law-Call-Id of the contested response.

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?

The description names a specific action ('Un SIGNALEMENT d'écart') and resource ('entre la formalisation et la source') and enumerates the four kinds of discrepancy it covers. It is clearly distinct from all sibling law_* tools because it explicitly says it does not alter law or other tools' answers.

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?

It gives a clear context for use: a report is a hypothesis for triage by a formalizer and covers concrete discrepancy categories. It also provides a strong implicit when-not-to-use warning ('il ne change PAS le droit, n'atteint jamais les réponses des autres outils'), though it does not name any alternative tool.

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