etablissement_by_finess

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

Annotations already indicate read-only and idempotent behavior. The description adds significant value by detailing the response format (discriminated LookupResult), explaining found/not_found structure, disclosing DREES repository lag, and noting that email is always null. It also mentions the cache behavior for the optional parameter. This goes well beyond annotations.

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 well-structured with the purpose in the first sentence, followed by response details, data notes, and source. Every sentence adds value, but it is somewhat lengthy due to explicit response format details that may be redundant given the output schema. Could be slightly more concise.

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?

Given the tool's complexity (output schema, two parameters, annotations), the description covers the purpose, response structure, data source limitations, a specific field note (email null), and cache behavior. It also advises cross-checking for emerging structures. This provides sufficient context for an agent to 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?

Input schema has 100% description coverage, so the baseline is 3. The description adds context: num_finess is exactly 9 digits, include_freshness adds a freshness field and has a 5-min server cache with negligible cost. This provides useful nuance over the schema alone.

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 retrieves full details of a health establishment by its FINESS number. It uses specific verbs ('Récupère le détail complet') and specifies the resource (établissement de santé par numéro FINESS), distinguishing it from sibling tools that handle lists, categories, or radius queries.

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 explains when to use the tool (for detailed lookup by exact FINESS) and notes data limitations (DREES lag, email null). It provides a cross-check recommendation for emerging structures. However, it does not explicitly state when not to use this tool or mention alternative tools for different use cases, which would improve guidance.

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