Préparer un rendez-vous client

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

The annotations indicate read-only and idempotent behavior, but the description goes further: it explicitly says no Boond API is called, no data is read, the response is generated server-side, and the returned runbook is only for the model to execute afterward. This prevents an agent from expecting live data or side effects.

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 front-loaded with purpose and uses compact, well-labeled sections for when to use it, what to prefer instead, and what it returns. Minor redundancy between 'N'appelle aucune API BoondManager et ne lit aucune donnée' and 'rien n'est fait par cet appel' keeps it from a perfect score.

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 defines the return value as a text runbook containing ordered Boond calls with exact filters, clarifies that nothing is executed by the call itself, and explains the alternative prompt path. Together with the schema-covered parameters, an agent has everything needed to select and invoke this tool 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?

The input schema already describes both parameters fully: society_id accepts an ID or name with auto-resolution via boond_companies_search, and horizon_jours has a default of 90. The description adds no parameter-level meaning beyond the schema, so with 100% schema coverage the 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 opens with a concrete deliverable ('brief de rendez-vous') and enumerates its contents: contacts, current opportunities, projects and services, unpaid invoices, recent exchanges, and topics to cover. It then positions the tool as a runbook generator that makes no Boond API calls, clearly distinguishing it from the many direct data-retrieval sibling tools.

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' paragraph states the intended trigger: running a multi-step scenario without the model having to rediscover the tool chain and exact filter names. The 'Plutôt que' paragraph names the MCP prompt alternative and the exact condition for choosing this tool instead (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.