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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, which covers the safety profile. The description adds meaningful behavioral context by specifying what the tool computes (averages, ranges, shares) and how the scope changes with or without a department. This goes beyond the annotations and helps the agent understand the nature of the response.

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 exceptionally concise: two sentences pack the tool's purpose, the indicators returned, the recommended usage moment, and the default geographic scope. It is front-loaded with the resource and question being answered, followed by actionable guidance. No filler or redundancy.

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 only two simple parameters and no output schema, the description is complete. It tells the agent what the tool returns, when to call it, and what happens if the optional parameter is omitted. The absence of an output schema is mitigated by the description's enumeration of the indicators, which effectively describes the return content.

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%, as both 'secteur' and 'departement' already have clear descriptions. The description adds minor context by clarifying the sector can be a CPV code or label, and that the territory is a department with France-wide fallback, but it largely echoes what the schema already states. Thus the description does not substantially enhance parameter understanding beyond 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?

The description clearly defines what the tool does: it returns market statistics (average number of offers, amount ranges, share of adapted procedures, share of framework agreements) for a purchasing sector on a territory. It also distinguishes it from sibling tools by framing it as the call to make 'avant de décider de candidater', which positions it as a market-analysis tool rather than a direct procurement search.

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 explicitly states when to use the tool: 'À appeler avant de décider de candidater'. It also explains the default behavior when no department is provided ('la réponse porte sur la France entière et sert de repère'). It does not explicitly mention when not to use it or name alternatives, but the context is clear enough to guide selection.

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