Marge d'un projet : simulé vs réalisé

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

Beyond the readOnly/idempotent annotations, the description discloses that it 'N'appelle aucune API BoondManager et ne lit aucune donnée' and that the response is generated server-side as a runbook. It also states that the model must execute the calls afterward, which is a non-obvious behavioral trait an agent needs to set expectations correctly.

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 and front-loaded: outcome first, then when to use, alternative, behavior, and return value. It is economical, though there is minor redundancy between 'N'appelle aucune API...' and 'rien n'est fait par cet appel', which prevents 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?

With no output schema, the description fully covers the return value: a textual runbook with the ordered Boond calls and exact filters, and the explicit instruction that the model must execute them. Combined with full schema parameter documentation and clear annotations, the agent has everything needed to invoke 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 description coverage is 100%, and the schema already documents both parameters well, including the date-range format and `project_id` auto-resolution via `boond_projects_search`. The description adds no parameter-specific detail beyond framing the project comparison scenario, so the 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 states a concrete scenario ('Compare le chiffre d'affaires, les coûts et la marge simulés d'un projet à son réalisé... prestation par prestation') and immediately clarifies the actual deliverable is a runbook rather than a live data call. It also distinguishes itself from sibling data tools by explicitly saying it calls no API and reads no data.

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' block explicitly tells an agent when to use this tool: to run a multi-step scenario without figuring out the tool sequence and filter names. The 'Plutôt que' block names the preferred alternative (the MCP prompt `marge_projet`) and the condition for choosing this variant, so the agent has clear routing guidance.

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