Devis et propositions à relancer

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

The description goes well beyond the readOnly/idempotent annotations by disclosing that the tool calls no BoondManager API, reads no data, and generates its response server-side. It also states the output is an ordered text runbook that the model must execute, preventing the agent from assuming side effects or real data retrieval. No contradiction 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 compact and front-loaded, with clear separation between purpose, usage conditions, alternative, and return contract. The critical 'no API/no data' caveat is a standalone bullet, and every sentence 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?

Despite having no output schema, the description fully specifies the return value: a text runbook with ordered Boond calls and exact filters. It also explains the division of labor, default scoping, and why this variant exists, leaving no critical gap for an agent to call it correctly.

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 both parameters are already richly documented in the input schema: manager_id covers formats, resolution via boond_resources_search, and default perimeter; jours_sans_action covers the default of 15. The tool description itself adds no additional parameter-level semantics, so the high-coverage baseline of 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 description opens with a specific verb and resource: it finds opportunities in 'proposition envoyée / négociation' phase with no action for N days and prepares follow-ups. It clearly frames the tool as a multi-step workflow runbook, and the French title distinguishes it from sibling workflows such as relance_cra or factures_a_relancer.

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 gives an explicit 'Quand' section and an explicit 'Plutôt que' alternative: use this tool to run the multi-step scenario without looking up the correct tool chain and filter names, and prefer the `relance_devis` prompt when exposed because it is identical and avoids a tool call. This provides a clear decision rule for the agent.

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