Audit fraîcheur des CV / dossiers techniques

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 a significant behavioral trait: it returns a textual runbook that the model must subsequently execute by calling referenced Boond tools, meaning the tool itself does not directly modify data. It also discloses prioritization behavior (focusing on intercontract or short-term availability).

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 three sentences long, front-loaded with the core purpose, and then explains its relationship to the MCP prompt and the runbook output. It is concise but includes a slightly meta reference that could be trimmed; overall it earns its place.

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 carries the burden of explaining what the tool returns, and it does: a textual runbook for follow-up execution. It also explains the input scoping behavior (manager targeting) indirectly via schema, and mentions prioritization. However, it doesn't detail the runbook structure or specific Boond tools to be called, which could be more complete.

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% for the two parameters (manager_id and seuil_mois), each with detailed descriptions. The tool description does not add meaningful information beyond the schema for these parameters, so the baseline 3 applies. The prioritization mention loosely relates to seuil_mois but doesn't add syntax or format details.

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 states the tool's function: identifying resources with outdated, incomplete, or missing CVs/technical files, and prioritizing those soon available on the market. This is a specific verb+resource combination that distinguishes it from sibling workflow tools like boond_workflow_synthese_equipe or boond_workflow_pipeline_commercial.

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 provides a clear usage context by stating it is the tool equivalent of the MCP prompt `cvs_a_mettre_a_jour`, and is useful for clients that don't handle MCP prompts correctly (e.g., claude.ai). This implies an alternative (use the prompt directly for capable clients), though it doesn't explicitly compare to other Boond workflow tools.

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