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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the result is a prospective recommendation rather than a historical line-by-line audit, and it guarantees that when no offer beats the current contract, recommended_offer never points to a more expensive catalogue offer. It stops short of covering engine-version behavior or cost/rate characteristics.

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?

Four dense sentences with the purpose and the sibling disambiguation front-loaded, followed by scope boundary, output guarantee and input prerequisite. Every sentence carries information, though the output-guarantee clause is unusually granular for a description this length.

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 an output schema present, annotations covering the safety profile, and full parameter documentation, the description supplies exactly the missing layer: scope (already-extracted bill vs raw PDF), the alternative tool, the prospective nature of the verdict, and the key output guarantee. Nothing an agent needs to call it correctly is absent.

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% across all 9 properties, including the HP/HC conditional fields and the optional cost reference, so the schema already carries the parameter meaning. The description only gestures at 'champs structurés' and the PDF-extraction prerequisite, adding no syntax or format detail beyond the schema. Baseline 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?

States a specific verb (évalue/analyse) applied to a precisely scoped resource: a residential bill that has already been extracted into structured fields, analyzed via the versioned engine. It explicitly distinguishes itself from the sibling 'simulate' and from the historical audit tools, so an agent can route correctly without opening any schema.

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?

Names the alternative ('pour une estimation sur paramètres sans facture, appelez simulate') and the condition that selects it, and rules out a competing interpretation ('pas du contrôle historique de toutes les lignes facturées'). It also states the prerequisite ordering: extract the PDF upstream, then call this tool with the fields.

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