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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the description's added value is real: it discloses that distance, current fuel price and commune CFE rates are auto-filled, meaning the agent need not supply them, and it specifies a returned address that should be cited. Error behavior for an unknown slug is not covered.

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 sentences, front-loaded with the verb and scope; the long parenthetical example list is informative but slightly overlong. The auto-completion and citation instructions are distinct, actionable sentences with no filler.

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, two-parameter compute tool with full schema coverage and rich annotations, the description supplies what the structured fields cannot: domain coverage, auto-filled inputs, and the fact that a detailed calculation page URL is returned (no output schema exists). Only failure/invalid-slug behavior is missing.

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 coverage is 100% and both parameters (slug, values) are documented in-schema, including the pointer to get_calculator/get_quote for field keys, so baseline 3 applies. The description's note that missing fields take defaults is reinforced by the schema but adds no key-level detail.

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 and resource ('Exécute un calculateur ou simulateur Vitef') and enumerates concrete domains (salaire brut en net, indemnité de licenciement, frais de notaire…), so the agent knows exactly what the tool computes. It does not, however, distinguish itself from the similar-sounding estimate_quote or explain the split with get_calculator/get_quote, which is left to the 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?

Usage is only implied: run a calculation and cite the returned address. There is no explicit when-to-use, when-not, or routing to estimate_quote / get_calculator / list_calculators, so an agent facing a quote-like request has to guess.

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