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

With no annotations provided, the description carries the full transparency burden. It clearly discloses what the tool returns (risk score, high-risk months, average frequency, recommendations) and the underlying data sources (Alim'confiance, DGCCRF), which gives the agent a solid understanding of the tool's behavior. It falls short of explicitly stating it is a read-only operation, but this is strongly implied by the 'get' verb and the estimation nature.

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 front-loaded with the core purpose and provides structured output details. It is duplicated in French and English, which adds length, but each language version is clear and the bilingual approach may serve multilingual agents. No unnecessary filler is present.

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 tool with no output schema and no annotations, the description gives a comprehensive picture: it lists all output components, cites data sources, explains the underlying logic (surge periods), and provides automation context. It does not specify the exact return data structure or error handling, but the described output fields are sufficient for an agent to understand and invoke the tool correctly.

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 baseline is 3. The description repeats that 'type_etablissement' and 'departement' are required but adds no additional meaning beyond the schema descriptions, which already explain the department code format, allowed establishment types, and that 'dernier_controle_ddpp' is optional and refines the risk score.

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 clearly states the tool returns an estimated DDPP inspection risk level for a given establishment type in a French department. It specifies the output components (risk score, high-risk months, frequency, recommendations) and distinguishes itself from sibling tools like get_alimconfiance_etablissement or get_score_alimconfiance by focusing on a composite risk estimate based on multiple data sources.

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 provides clear usage context, explicitly noting it is designed for automation and should be called quarterly to adjust vigilance. It does not explicitly exclude alternatives or compare with sibling tools, but the automated quarterly cadence gives a concrete when-to-use scenario.

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