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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description adds real behavioral value with no output schema present: it discloses the returned content (level-by-level, status, latest result) and the fact that carte scolaire publication status is reported, plus the arrondissement special case for Paris/Lyon/Marseille.

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?

Two sentences, front-loaded with the resource being returned, and the arrondissement caveat is efficiently appended. No filler, though the first sentence is dense and packs several concepts into one clause chain.

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 with no output schema, the description carries the needed burden: it says what is returned and the one tricky input case (arrondissements). Gaps remain around result granularity ('dernier résultat' of what?) and response shape, but the tool's complexity is low.

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% – code_insee is fully documented with a pattern and an example (49007 Angers) – so baseline would be 3. The description adds a parameter-relevant nuance by flagging that Paris, Lyon and Marseille count arrondissements, hinting that their codes may be arrondissement INSEE codes rather than the commune itself.

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 states a specific resource and scope: the establishments of one commune, broken down 'niveau par niveau' with their status and latest result, plus whether the collège/lycée catchment map is published. This clearly distinguishes it from the single-school siblings (get_french_school, get_french_school_ranking, get_french_school_sectors), though it never names those alternatives explicitly.

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?

Usage is only implied – an agent infers 'use this to list all schools in a commune'. The note that Paris, Lyon and Marseille count arrondissements is a genuinely useful usage nuance, but no explicit when-to-use/when-not or alternative tool is offered.

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