Recherche multi-source d'un profil par compétences

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds crucial behavior: it explicitly states 'N'appelle aucune API BoondManager et ne lit aucune donnée' and that the response is generated server-side. This goes beyond the read-only hint by explaining that no external data is touched at all—important for a tool that only produces instructions. No contradictions with annotations.

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-structured with a clear first-line summary, then a 'Quand' section, a 'Plutôt que' section, and a 'Returns' section. Every sentence adds value: it explains the multi-step nature, the alternative, the no-API behavior, and the output format. No fluff or repetition; front-loaded with the core purpose.

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 workflow tool that returns a runbook, the description covers all necessary context: what it does, when to use it, what it returns (a text runbook), and that it does not execute anything. It also explains the reasoning for its existence (prompts/get compatibility). Given no output schema, it explicitly describes the return format. Nothing an agent needs to decide whether to invoke it 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%: each parameter already has a detailed description (e.g., manager_id accepts ID or 'Prénom Nom', dispo_avant applies period/endDate). The tool description does not add significant meaning beyond that; it mentions 'mix de compétences libres' and that filters will be exact, but these are not parameter-specific. Baseline of 3 applies because the schema carries the semantic weight.

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 purpose: it searches for a profile matching a mix of free-form skills, crossing internal resources and candidates, and outputs results ranked by fit. It also frames the use case ('en amont d'un staffing ou d'une opportunité non encore qualifiée') and distinguishes it from sibling direct-search tools by clarifying it returns a runbook rather than executing queries. This is a specific verb+resource with a well-defined scope.

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 says when to use it ('Quand : pour dérouler ce scénario multi-étapes') and names a concrete alternative ('Plutôt que le prompt MCP recherche_profil_competences'), even explaining why this variant exists (for clients that handle prompts/get poorly). This gives the agent clear routing logic and no ambiguity about when to choose it over siblings.

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