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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is low, yet the description adds substantial method disclosure: 2,000-inhabitant and 10-sales thresholds, DVF source for price rankings, a 30-commune cap plus total-count reporting, and the 'Aucun score Pillr' caveat. These are exactly the traits an agent needs to interpret results without over-claiming.

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?

Purpose and criteria come first, then methodology, then the alternative-tool routing and exclusions – well front-loaded with no filler sentences. It is dense with numbers in the middle, which costs a little readability but every clause carries information.

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 still conveys return shape (at most 30 ranked communes plus the total number ranked) and the data basis. Combined with the exclusion list, an agent has enough to call it correctly and describe its output honestly.

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 schema already spells out each enum value and its sort direction, so the description's restatement of the three criteria adds little beyond it. The depiction thresholds (population, sales) inform result interpretation but not the parameters themselves, so 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?

Opens with a specific verb and resource ('Classe les communes d'UN département selon un critère public') and immediately scopes it to a single department and a named criterion set. The capitalised 'UN' plus the ranked-list framing make it unmistakably distinct from per-commune siblings like prix_m2_commune or marche_commune.

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 concrete when-to-use examples ('où investir en Gironde', 'les communes les moins chères du Nord'), names the explicit alternative for the opposite case (comparaison_communes for already-named communes), and states exclusions (Paris, Bouches-du-Rhône, Rhône are not ranked). Nothing is left to inference about when to pick this tool.

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