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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the input disambiguation priority (unprefixed five digits read as postal code first) and the ambiguity-resolution flow that returns multiple communes with a relaunch query. It stops short of describing pagination or latency, but no output schema exists and the return content is summarized.

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?

Content is front-loaded: purpose, accepted input forms, ambiguity handling, then return contents and sources. It is dense and long, but since no output schema exists, the enumerated return fields and source/cadence notes largely earn their place rather than repeating structured metadata.

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 complex domain tool with one parameter and no output schema, the description supplies everything an agent needs: accepted identifier formats, ambiguity fallback, a detailed account of returned data, and the upstream sources with millesime and refresh cadence. Nothing material is missing.

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 there is only one parameter, so the baseline would be 3. The description goes beyond the schema by specifying the disambiguation order ('sans préfixe, 5 chiffres se lisent d'abord comme un code postal') and richer examples, actively clarifying how a single string argument is interpreted.

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 ('Analyse l'accès aux soins d'un territoire français') and enumerates exactly what is returned, so an agent knows it is a single-territory healthcare-access analysis. It does not explicitly distinguish itself from the sibling compare_territories, which is left to inference from 'un territoire'.

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 thoroughly covers how to supply input (postal code, commune name, INSEE prefix) and how to recover from ambiguity via relancer_avec, which implies usage. However, it never states when to prefer this over siblings such as compare_territories, search_health_infrastructure or qui_saisir, and gives no exclusions.

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