Pipeline commercial sur une période

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

The description explicitly discloses that the tool makes no API calls and reads no data, with the response generated server-side. This is valuable behavioral context beyond the annotations (readOnlyHint, idempotentHint, destructiveHint). It also clarifies the return type (a runbook text) and that the model must execute the listed calls afterward. Minor gap: no mention of error cases or what happens if the period is invalid, but the core non-execution behavior is well disclosed.

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 clear sections (Quand, Plutôt que, Returns) and front-loads the core purpose. It's slightly verbose with the explanation about prompts/get handling, but every sentence serves a purpose in guiding tool selection and expectations. The formatting aids readability for an agent.

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 tool that returns a runbook rather than data, the description adequately covers what the agent needs: the purpose, the alternative, the non-execution behavior, and the return format. The absence of an output schema is compensated by the explicit 'Returns : un runbook en texte' statement. Minor gap: no example of the runbook format or the exact filter names, but the description states the runbook will contain them, which is sufficient for selection.

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%, so the schema already documents all three parameters. The description adds context for `manager_id` by explaining the resolution via `boond_resources_search` and the default scope, but this is already in the schema description. The description doesn't add much beyond the schema, so baseline 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 function: analyzing commercial opportunities with closing in a given period, providing distribution by state, weighted revenue, and top opportunities. It distinguishes itself from the sibling `pipeline_commercial` prompt and other workflow tools by explicitly stating it's a multi-step scenario runner that returns a runbook rather than performing data operations.

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 states when to use this tool ('pour dérouler ce scénario multi-étapes sans avoir à retrouver soi-même le bon enchaînement d'outils'), and provides a clear alternative ('Plutôt que : le prompt MCP `pipeline_commercial` si le client l'expose'). It also explains the fallback rationale for clients that handle prompts/get poorly, giving an agent clear routing logic.

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