Préparer un entretien candidat

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

Beyond the readOnly/idempotent/destructive annotations, the description explicitly states 'N'appelle aucune API BoondManager et ne lit aucune donnée', that the response is generated server-side, and that 'rien n'est fait par cet appel.' This fully discloses the no-side-effect, no-data-fetch behavior and sets accurate expectations that the model must execute the returned runbook afterward.

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 front-loaded purpose and clear labeled sections ('Quand', 'Plutôt que', 'Returns'), making it scannable for an agent. It is somewhat redundant around the no-API/no-data-read behavior, repeated in three different phrasings, which keeps it from earning a 5.

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 with no output schema, the description fully covers what the agent needs: when to use it, what it returns ('un runbook en texte — la liste ordonnée des appels Boond'), that nothing is executed, and how the parameters relate to the scenario. The schema already documents the parameter types and resolution behavior, so no essential choice or invocation details are 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?

The input schema already provides 100% coverage with detailed descriptions for both parameters, including auto-resolution through `boond_candidates_search` and `boond_opportunities_search`. The tool description adds little beyond reinforcing that opportunity_id is used when an opportunity is targeted, so it does not meaningfully increase parameter understanding beyond the schema baseline.

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 names the target resource (candidate, optional opportunity) and the workflow action ('Rassemble en une fiche... confronte le profil au besoin'), and it clarifies that the output is a runbook of API calls rather than executed work. It is distinguishable from sibling tools by its 'préparer entretien' focus and multi-step orchestration. However, the first sentence slightly conflicts with the later claim that the tool reads no data, since 'rassemble... tout ce que BoondManager sait' can be read as actually consolidating data rather than generating a plan.

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 has an explicit 'Quand' section explaining to use it when the agent needs a multi-step scenario without rediscovering the tool chain and filter names. It also provides a direct alternative ('Plutôt que : le prompt MCP `preparation_entretien`') with the condition of when that prompt should be preferred, including the compatibility caveat for clients that handle `prompts/get` poorly.

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