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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds provenance context beyond the annotations, notably that prices come from real sales ("ventes réelles") and rents are observed rather than modeled, plus the IMS score broken out by strategy. It does not describe pagination, response shape, or what happens when the partial neighborhood name matches several IRIS entries, which is the main residual risk for this tool.

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 what the tool returns and closed with the required inputs. Dense domain vocabulary (IRIS, IMS Market Score) is used without explanation but each listed aggregate earns its place by telling the agent what data comes back.

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 and two required parameters, the description carries the burden of explaining return values, and its enumeration of aggregates largely does that. However, it leaves undefined what an IRIS is, what the IMS Market Score scale means, and how ambiguous partial-name matches are resolved, so an agent still lacks some context for interpreting results.

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 50 percent: only "quartier" carries a schema description, while "ville" is undocumented in the schema. The description compensates by clarifying both inputs, stating that the city is given directly and that a full or partial neighborhood name is acceptable ("un morceau du nom du quartier"), which is meaningful beyond the raw schema.

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 resource (IMMONAI aggregates for an IRIS neighborhood of a city) and enumerates its contents: reference price per m² from real sales, observed rents per m², gross yields, IMS Market Score by strategy, and neighborhood quality/safety. It does not name the siblings classement_quartiers or methode_score, so an agent must infer the boundary from the differing resources, but the verb+resource pairing is concrete and not tautological.

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 closing sentence gives a calling instruction (supply the city and a fragment of the neighborhood name), which is useful procedural guidance. It never states when to choose this tool over classement_quartiers (ranking) or methode_score (scoring method), and no exclusions or prerequisites are given, so usage is only implied.

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