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

With no annotations, the description carries the full burden, and it does disclose output shape (unit price, per-line assumptions, explicit exclusions) plus a quantity basis ('1 unité'). It omits operational traits that matter for this API family, notably credit consumption (cf. recharger_credits, consulter_usage) and what happens if required plan inputs are missing.

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?

A single front-loaded sentence beginning with the verb, with no filler; each clause (unit price, line items with assumptions, exclusions) carries information. It is dense but not padded.

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?

There is no output schema, and the description compensates well by describing the returned breakdown. But for a cost-generating tool with a nested 'ajustements' object that self-references ('voir ajustements_possibles dans la réponse'), the absence of any credit/cost or failure-mode context leaves gaps.

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 71%, so the schema already documents most parameters (matiere, plan_id, epaisseur_mm, lot_de_fabrication). The description only touches matière and plan_id indirectly and adds '1 unité', which arguably relates to quantite but is not clearly tied to a parameter name, so it adds little beyond the schema.

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?

States a specific verb (chiffre/cost) and resource (pièce usinée) and even enumerates the output breakdown (prix unitaire, lignes matière/opérations/frais/marge). It does not explicitly contrast itself with siblings like verifier_devis or comparer_quantites, so it stops short of 5.

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 phrase 'depuis un plan déposé' implies the prerequisite that a plan must first exist (cf. deposer_plan), which is a usable usage cue. However, there is no explicit when-to-use/when-not and no routing to alternatives such as verifier_devis, leaving selection largely to inference.

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