Traiter un justificatif en note de frais

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

Beyond the readOnly/idempotent annotations, the description discloses that no Boond API is called, no data is read, the response is generated server-side, and the tool returns a textual runbook for the model to execute. It also adds the no-invented-amount and user-request-for-illegible-field behaviors; only the earlier 'crée la ligne' phrasing slightly muddles this otherwise transparent picture.

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 text is organized into clear sections (Quand, Plutôt que, Returns) with the key constraints front-loaded and no filler. It is a bit long and repeats the no-API idea, but each section 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?

The description covers when to use it, the alternative to prefer, side-effect guarantees, the return format, validation, and how illegible fields are handled—especially valuable given there is no output schema. A short example or a less contradictory opening sentence would make it fully complete.

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?

Input-schema description coverage is 100%, so the schema already explains all four parameters, including the auto-resolution behavior for project_id and resource_id. The tool description adds no parameter-level detail beyond that, so it stays at the schema-covered baseline.

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 names a concrete scenario and outcome—extract data from a receipt and create an expense line in BoondManager after explicit validation—and states a clear invariant (no invented amounts). It is not a tautology and is specific enough to distinguish from most siblings, but the first sentence says the tool itself creates the line while the Returns section says it only emits a runbook, which leaves the tool's immediate effect slightly ambiguous.

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 says this tool is for running a multi-step workflow without manually chaining tools and filters. The 'Plutôt que' block names a specific alternative (the MCP prompt `traiter_note_de_frais`) and gives the condition under which each should be chosen, so an agent needs no inference.

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