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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds behavioral value beyond annotations: 'Jamais un chiffre nu' promises a provenance-rich response, and the list of returned fields (source primaire, référence légale, date de vérification, niveau de fiabilité) tells the agent what to expect. It also implies unknown-key handling via redirection to referentiel_recherche.

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?

Four sentences, each earning its place: purpose, return characteristics, fallback guidance, and data source. The opening phrase 'Valeur du référentiel (sourcée + datée)' duplicates the annotation title, a small redundancy, but the rest is compact and front-loaded with the core behavior.

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 single-parameter lookup tool with no output schema, the description compensates reasonably: it enumerates the provenance fields returned and gives the fallback tool for invalid keys. It does not spell out the exact JSON envelope or error codes, but an agent has enough to call it correctly and interpret the response.

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 the parameter description already provides stable-key semantics, examples, and a pointer to referentiel_recherche. The tool description adds minor context ('2026', 'constante fiscale ou retraite') but no new parameter-level meaning beyond what the schema already states, so the baseline 3 is appropriate.

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: returns the sourced and dated 2026 value of a fiscal or retirement constant by its stable public key, with source, legal reference, verification date, and reliability level. It also distinguishes itself from the search sibling by adding 'Clé inconnue → referentiel_recherche', making the lookup-vs-search split explicit.

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?

Gives an explicit alternative condition: unknown key → referentiel_recherche to list available keys. This is clear guidance for the main decision an agent faces. It does not mention referentiel_versions for historical/versioned lookups, but the 2026 framing and the named fallback cover the common case.

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