Fiche complète d'un collaborateur

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

The description discloses a key behavioral trait beyond annotations: it returns a runbook text rather than direct data, which the model must execute by calling other Boond tools. This is significant for a read-only tool, as it explains the indirect nature of the operation. It also emphasizes the 360° aggregation, adding value beyond the standard readOnlyHint.

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 concise, consisting of two sentences that efficiently cover purpose, use case, and behavior. It opens with a clear summary, then adds contextual and operational details without redundancy. Every clause 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?

For a workflow tool with one parameter and no output schema, the description is complete. It explains what the tool returns (a runbook), how to use it (execute the referenced tools), and its intended scenario (MCP-incapable clients). No essential context is missing for the agent to decide and act.

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 provides complete documentation for the sole parameter `resource_id`, including both accepted formats and automatic resolution via `boond_resources_search`. The description itself does not add any additional parameter semantics; since schema coverage is 100%, a baseline of 3 is appropriate.

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 with a specific scope: 'Vue 360° d'une ressource : info, profil technique, positionnements, absences, CRA récents.' It identifies the resource type and the aggregated data categories, distinguishing it from simpler get tools. It further differentiates from siblings by noting it's an equivalent of an MCP prompt, making it a unique workflow tool.

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 use case: 'utile pour les clients qui ne gèrent pas correctement les prompts MCP, ex: claude.ai'. It also instructs how to handle the output ('Retourne un runbook texte que le modèle doit ensuite exécuter'). However, it does not explicitly state when not to use it or provide direct alternatives among the sibling tools, falling short of full exclusion guidance.

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