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

Annotations already establish read-only/idempotent/non-destructive, so the bar is lower; description adds real value by explaining the single-lot-sales filter and the DVF double-counting rationale, and by disclosing the surprising fallback where an ambiguous name returns a candidate list instead of a number. It does not cover empty-result behavior or any limits, but the annotation-covered safety profile plus the methodology note is solid.

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 outputs are front-loaded, with the methodology and parameter notes following in a single dense but well-ordered paragraph. The DVF double-counting explanation is long but earns its place for a tool with no output schema; nothing is padding.

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 communicates the returned measures (median, average, transaction count) and the alternate candidate-list return, which is the main thing an agent needs. Missing only edge-case return shapes (e.g., zero transactions) and exact field names.

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 documents both the year format and the INSEE-code/name duality of commune, including the arrondissement-expansion behavior. The description largely restates that (adding only a second ambiguous-name example, "Saint-Martin"), so it meets the baseline 3 rather than exceeding it.

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 verb+resource+scope: median/average price per m2 for a French commune and year, broken out by Maison/Appartement, plus transaction count. An agent can distinguish this statistical-aggregate tool from the raw-sale siblings (fr_property_sale, fr_property_sales) 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 concrete triggering examples ("median price per m2 in Lyon in 2024", "how much do apartments go for in Nantes"), plus the key usage condition that a bare multi-commune name returns candidates rather than a number. It never explicitly names fr_property_sale/fr_property_sales as the alternatives, so the when-not-to-use side is left implicit.

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