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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint, lowering the bar; the description still adds meaningful context beyond them: the versioned engine, the explicit stay/switch and per-offer tariff output, and a specific edge-case guarantee that recommended_offer never points to a pricier catalog offer when nothing beats the current contract. The JSON-only note is an actionable transport constraint.

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?

Three dense sentences with no filler: purpose is front-loaded, then output behavior, then the usage constraint. Every sentence earns its place relative to the 9-parameter schema and the output schema.

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?

For a read-only analysis tool with a full output schema and 100% parameter coverage, the description covers purpose, output behavior, and the required upstream extraction step. The only gap is explicit routing among the many sibling analysis tools (analyze_renewal_terms, simulate, assess_*), but that is not essential to making a correct call.

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% — every parameter already has a meaningful description, so the baseline is 3. The tool description only refers generically to 'les champs' and adds no parameter-specific meaning beyond what the schema already provides.

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 precise verb+resource: analyzing an already-extracted residential electricity bill via the versioned engine. The qualifier 'déjà extraite' plus the explicit stay/switch verdict separates it from extraction siblings (extract_energy_document) and simulation/analysis siblings without opening their schemas.

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 description gives a clear workflow precondition: extract the PDF first, then call with structured fields, and warns that MCP is JSON only. This tells the agent where in the pipeline to invoke the tool, though it does not explicitly name alternative sibling tools or state when-not-to-use conditions.

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