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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: a cost of 10 credits, the exact decade buckets returned, and a concrete row shape including nb and vs_zone_pct. It stops short of describing coverage when a decade has no transactions.

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-loaded with the core purpose, then bucketed facts, requirements, and an example; the bucket enumeration and sample row are domain-specific and earn their space. The advisory sentence is slightly promotional but still conveys use, and the block layout is easy to scan.

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 read-only analytical tool with no output schema, the definition supplies requirements, filter options, the returned bucket labels, an example record, and cost — enough to call it correctly. Minor gaps remain around the meaning of nb and results when a decade is empty, but these are not blocking.

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%, so the baseline would be 3, but the description adds a constraint the schema does not express: that at least one of code_postal, commune, or code_departement must be supplied (the schema has zero required properties). It also restates type_local's role, so it meaningfully supplements rather than repeats the 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 precise verb and resource: median prix/m² grouped by construction decade for a location, and explicitly frames the output as a premium/discount versus the area median. This is clearly distinguishable from sibling analyses such as analyze_price_trends or get_zonal_price_distribution, which do not cross price by building age.

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 the intended decision context ('advising whether older buildings trade at a discount and how much') and the input prerequisites (at least one location; optional type_local filter). It does not explicitly say when to prefer a sibling tool or what to do if no location resolves, leaving some routing to inference.

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