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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds substantial non-obvious behavior: provenance is either measured from DVF sales or estimated, Paris/Lyon/Marseille returns counts of measured and estimated arrondissements, and missing prices are reported as absent and never guessed. This enriches the annotations without contradicting them.

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 description is moderately long but front-loaded, opening with the core purpose before diving into details. Each sentence earns its place: the first enumerates return fields and provenance nuances, the second clarifies the absent-price behavior, and the third scopes the tool. Minor redundancy in 'absent is said absent, never guessed' does not significantly hurt clarity.

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?

Despite having no output schema, the description enumerates the returned elements (value, provenance, millésime, reconstruction date) and the aggregation behavior for Paris, Lyon, and Marseille. It also describes the edge case for missing prices and the non-goal of property-specific valuation. With rich annotations and a fully documented single parameter, nothing essential for correct invocation is missing.

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?

The single parameter 'commune' is fully documented in the schema with 100% coverage, including name formats, INSEE codes, arrondissement variants, and postal-code fallback. The description adds no additional parameter meaning beyond the schema, so the baseline of 3 applies. The description's mention of arrondissement counting pertains to return data rather than input semantics.

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 precisely states the resource: reference price per square meter for a French commune, covering apartment and house, as published by Pillr. It enumerates the returned data (value, provenance, vintage, reconstruction date) and explicitly distinguishes itself from a specific-property appraisal, which also differentiates it from the sibling tools. This is a clear, self-contained statement of what the tool does.

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 description establishes the intended use context: a communal market benchmark, not an estimate for a specific property, which is an implicit exclusion. It does not name alternatives or give explicit when/when-not rules, but the stated scope makes the boundary clear. The sibling tools (demarche_urbanisme_projet, marche_commune) are sufficiently different that no routing ambiguity remains.

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