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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses result ordering (du plus cher au moins cher), the publication threshold (quartiers d'au moins 5 ventes), the cap (40 max per property type), and the meaning of the provenance field. It effectively documents the return payload in the absence of an output schema.

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?

Front-loads scope and granularity, then the exclusion rule and alternative. Dense and largely waste-free, though the long run-on first sentence mixing returned fields, thresholds and caps could be split for faster scanning.

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 two-parameter read tool with no output schema, the description covers what is returned (prix, nombre de ventes DVF, provenance, part), how it is ordered, what is suppressed, and how it differs from siblings. An agent has everything needed to invoke it correctly and interpret the result.

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%, with the commune parameter already explaining name/INSEE/arrondissement forms and the type_bien enum documented. The description reinforces the single-commune constraint but adds no parameter syntax or format detail beyond what the schema already provides, 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?

States a specific resource (prix au m² des appartements et maisons), a specific granularity (quartier par quartier, IRIS de l'INSEE) and a specific scope (UNE commune), then explicitly rules out the sibling prix_m2_commune. An agent can distinguish it from prix_m2_commune, marche_commune and comparaison_communes without opening any schema.

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?

Gives a concrete use-case («quel quartier est le moins cher à Lille»), a secondary use (situer un quartier dans sa commune), the explicit alternative for the commune-level question, and the negative condition (communes not split by INSEE into quartiers have no quartier price). It even routes Paris/Lyon/Marseille queries to arrondissement naming rather than a different tool.

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