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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds valuable behavioral context beyond that: Paris/Marseille/Lyon resolve to arrondissements, and the output mirrors the commune page .md twin, which tells the agent what to expect. No contradiction with 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?

Three sentences front-load the fact list and add one essential caveat. The .md twin phrase is slightly cryptic but concise and informative; there is no redundant filler.

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 no output schema, the description carries the burden of indicating what will be returned; it lists six fact categories and the special city behavior. It is complete enough for a single-parameter read-only tool, although the exact response format/markdown structure is left vague.

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 the code_insee parameter is already documented with pattern and an example. The description does not add parameter-format detail beyond that, so the baseline 3 applies; the arrondissement note is output behavior rather than parameter syntax.

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 enumerates the exact commune-level facts returned (voies adressées, median price, urbanism document, zone A/B/C, fibre eligibility, risks) and notes the arrondissement behavior for Paris/Marseille/Lyon. It is clear enough to differentiate from address, permit, and parcel siblings, though it lacks an explicit verb like 'returns' and reads as a noun-phrase definition.

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 content list makes the intended use implicit: call this for aggregate commune facts rather than address details, permits, or parcels. However, it never explicitly states when to prefer this tool over the siblings or mentions any exclusion conditions.

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