Cartographie des compétences d'un périmètre

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

Annotations already carry readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value beyond these by specifying the tool calls no BoondManager API, reads no data, generates its response server-side, and returns a text runbook for the model to execute — clarifying the actual behavioral contract. No contradiction with annotations; the only minor gap is not detailing the exact runbook structure.

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 well-organized and front-loaded: purpose first, then 'Quand', 'Plutôt que', the no-API note, and 'Returns'. Every sentence earns its place, though the French formal structure makes it slightly longer than strictly necessary. Information density is high with no wasteful repetition.

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 complex workflow-orchestration tool with no output schema, the description fully compensates: it explains the return value (a text runbook listing ordered Boond calls with exact filters), clarifies nothing is executed by the call, and states the alternate prompt path. Together with a 100%-covered optional-parameter schema, nothing an agent needs to call it correctly is missing.

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 the schema fully documents top_n, agency_id, and manager_id, including the automatic resolution logic. The description adds only marginal param-related context (the scope concept team/agency maps to agency_id/manager_id) but no syntax or format details beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb ('Produit une cartographie des compétences techniques d'un périmètre') with a precise resource and scope, enumerating the concrete outputs (top skills, rare skills/bus-factor risk, missing skills vs opportunities). It further distinguishes this tool from the MCP prompt `cartographie_competences`, making its identity unambiguous among the workflow siblings.

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 'Quand' section explicitly states when to use it (to run a multi-step scenario without manually finding the tool chain and filter names), and the 'Plutôt que' section names the exact alternative (the `cartographie_competences` prompt) and the condition that selects this variant (clients that handle `prompts/get` poorly). Clear when/when-not guidance with a named alternative.

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