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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely behavioral detail beyond that: prefix rather than substring matching, a hard result cap of 20 with a default of 5, and the fact that ambiguous names return multiple candidates. The licensing/dataset paragraph adds provenance but little invocation value.

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 first paragraph is well front-loaded and tight. The second paragraph is source/licensing boilerplate naming RPG 2025, BNVD 2024, SISE-Eaux and Rigal & Perrot — datasets this tool does not return — which dilutes the signal for an agent deciding whether to call it.

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?

With an output schema present, the description needn't explain return values, and it still summarizes them briefly. Annotations plus full schema coverage mean the agent has what it needs to call correctly; the only missing piece is a pointer to which sibling to use once a commune is identified.

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%, and the schema already states the default of 5, the maximum of 20, minLength 2 and prefix semantics. The description restates these rather than adding format examples (e.g. whether postal code '75' matches Paris) or edge-case behavior. 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?

The description gives a specific verb and resource ('Recherche de communes françaises par nom ou code postal') plus the matching mode (préfixe, ≥2 caractères), which an agent can act on directly. It does not explicitly contrast itself with siblings like compare_communes or rank_communes, but those operate on already-identified communes, so the lookup role is still inferable.

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: the reader must infer this is the discovery step that precedes department_profile, get_commune_exposure, etc. The ambiguity handling note ('un même nom existe souvent dans plusieurs départements') hints at the case where the caller should raise limit, but no explicit when-to-use or when-not-to-use statement is given.

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