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

Annotations already establish that the tool is read-only, idempotent, and non-destructive. The description adds useful behavioral context by clarifying that only actually awarded contracts are included ('réellement attribué') and by revealing the nature of the returned data (count, median budget, last order).

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?

Three short sentences cover purpose, output, usage context, and the required input format. There is no filler, and the main scoping information is front-loaded.

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?

Because there is no output schema, the description usefully names the returned aggregates so an agent knows what to expect. It covers the key use case and required parameter format; the only gaps are the optional 'limite' and 'secteur' behaviors, which are partly inferable from the schema.

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 67%: 'departement' and 'secteur' are documented, but 'limite' is not. The description's only parameter-related sentence repeats the schema's exact 'departement' format ('35', 'Ille-et-Vilaine') and adds no new meaning about 'limite' or 'secteur'.

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 uses a specific verb ('Liste') and identifies the exact resource: collectivités, hôpitaux and établissements publics that actually awarded contracts in a department. It also states the returned metrics (number of contracts, median budget, last order), which makes the tool's purpose concrete. The use-case phrasing 'à qui vendre / qui achète' distinguishes it from the sibling tools about sector statistics, open consultations, and company-specific contracts.

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 gives an explicit trigger: use this tool when the question is about 'à qui vendre' or 'qui achète' in a territory. It does not name alternative tools or state when not to use it, so it falls short of a full exclusion guide.

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