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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint/destructiveHint=false, so safety is covered. The description adds real behavioral context beyond them: the three city-to-arrondissement redirect behavior and the fact that the returned text is identical to the .md twin of the commune page. It still doesn't describe pagination or response size, so not a 5.

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 single enumeration sentence is long but front-loaded with the resource and every listed facet earns its place, since there is no output schema to convey the return payload. The trailing arrondissement/`.md` note is relevant, not filler. Slight run-on density prevents a 5.

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 only one well-documented parameter, no output schema, and annotations covering the safety profile, the enumerated return facets give an agent enough to know what it will receive. The main missing piece is response size/format expectations, but coverage is otherwise adequate.

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% — code_insee is fully documented with pattern and example (94081 Vitry-sur-Seine) — so the schema carries the parameter semantics. The description adds nothing about the single input parameter, so the baseline 3 applies.

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 declares a specific resource (a French commune) and enumerates concrete facets it returns: addressed streets, median price per m², rent, property tax rate, urbanism documents, A/B/C market zone, fibre coverage, risks, delinquency (SSMSI), tap water/PFAS. This is clearly a commune-level facts tool, distinguishable in kind from the sibling parcel/building-permit/address tools. It lacks an explicit contrast with those siblings, keeping it at 4 rather than 5.

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?

There is no explicit when-to-use guidance and no comparison to the sibling tools (get_french_parcel, get_french_building_permits). However, the closing note that Paris, Marseille and Lyon resolve to their arrondissements is a genuine usage rule that changes how an agent should call the tool. Usage is implied rather than stated.

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