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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely useful behavior: the DVF/DGFiP-Etalab provenance, that only the two most recent full years are returned, and that cells with fewer than 10 sales are suppressed — a disclosure rule an agent would otherwise not know.

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 the country and the returned metrics, followed by coverage scope, data source and the suppression caveat. No filler clauses; each phrase adds 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 carries the burden of describing returns and does so: median €/m², median price, sales count, two years of data. Combined with annotations and a fully documented schema, an agent has nearly everything needed, though the exact response shape (e.g., per-arrondissement breakdown) remains unstated.

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 description coverage is 100%, so the schema already documents ville, quartier and arrondissement. The description adds scope context (200 covered cities; arrondissement granularity limited to Paris/Lyon/Marseille), but that largely repeats what the schema already states, so 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 and scope: median price per m² (apartments and houses), median price and sales count for French cities/arrondissements/neighbourhoods, sourced from DVF. The 'FRANCE' prefix and DVF attribution implicitly separate it from the country-agnostic sibling stats_marche, but no sibling is named explicitly.

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 defines the coverage envelope (200 French cities, arrondissements of Paris/Lyon/Marseille, neighbourhoods) and the time window (latest full year plus the prior year), which implies when the tool is appropriate. It never states when to prefer it over stats_marche or another pricing sibling, so routing remains inferred.

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