Fiche complète d'un collaborateur

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 genuinely useful context beyond that: it reveals the tool makes no BoondManager API calls, reads no data, and returns an instruction runbook that the model must execute itself ('rien n'est fait par cet appel'). This is critical behavioral disclosure consistent with the 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 purpose is front-loaded and the usage guidance is tight and precise. There is minor redundancy: the point that the tool performs no API call and no side effect is stated twice ('N'appelle aucune API... ne lit aucune donnée' and 'rien n'est fait par cet appel'), which could be trimmed without losing meaning.

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 single-parameter workflow tool with strong annotation coverage (readOnly, idempotent, non-destructive), the description covers the essential ground: purpose, when to use, the alternative to prefer, behavioral reality (no API call), and return format (ordered runbook with exact filters). The agent knows what it receives and that it must execute the listed calls itself. Remaining gaps are minor.

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% and the resource_id parameter description in the schema is already rich — it documents both accepted formats (numeric ID or 'Prénom Nom') and the automatic resolution via boond_resources_search. Since the schema carries the full parameter documentation, the description itself adds nothing beyond it, so the baseline 3 applies.

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 opening line 'Vue 360° d'une ressource : info, profil technique, positionnements, absences, CRA récents' states a specific deliverable for a specific resource, and the Returns section clarifies it generates a runbook of calls rather than data. This clearly distinguishes it from the many direct-data siblings like boond_resources_get, boond_resources_information, and the other boond_workflow_* scenario tools, each with its own focused purpose.

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 states the exact trigger (running the multi-step scenario without figuring out the tool sequence), and 'Plutôt que' names the precise alternative (the `fiche_consultant` MCP prompt) along with the condition for choosing this variant (clients that handle prompts/get poorly, e.g. claude.ai). This is model-level routing guidance that leaves nothing to inference.

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