Cartographie sémantique du site

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavior beyond these: the default summary mode, the 'full=1' to get all data, and 'refresh=1' to trigger recalculation. It clarifies that the tool can recompute results, which is not implied by the annotations alone. No contradiction with annotations exists.

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 with dense but efficient information. The purpose is front-loaded, and parameter combinations are compressed into a list. The endpoint URL at the end is slightly redundant but harmless. Overall, it's well-structured and avoids fluff, though the density might make it less scannable than a more sentence-based format.

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 10 parameters and no output schema, the description gives a partial picture. It explains the summary output and the detail mode but doesn't describe what a 'detail' response contains or what the clusters represent beyond 'hors sujet'. The meaning of sort values is left to the schema, and interactions like how 'cluster' and 'page_id' combine are unspecified. This is adequate for a basic call but not fully complete for complex usage.

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 parameters are individually documented. The description adds value by grouping parameters into modes (summary vs detail), explaining the effect of 'full' and 'refresh', and indicating which parameters apply to the detail view. This goes beyond the schema's per-parameter descriptions and helps the agent understand how to combine them.

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 identifies the resource as 'Cartographie sémantique du site' and implies a retrieval action. It clarifies the default output as a summary of clusters and the 50 most off-topic pages, giving a concrete sense of what the tool returns. It distinguishes itself from siblings because no other tool mentions semantic mapping, though it doesn't explicitly state the verb (get) or differentiate from potential similar tools.

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 explains parameter-driven behavior (default summary vs detail, full=1, refresh=1) but provides no guidance on when to choose this tool over alternatives. There are no exclusions or comparisons to sibling tools, leaving the agent to infer that this is the only semantic map tool. This is a clear gap in routing guidance.

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