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

Annotations already mark the tool readOnly and non-destructive. The description adds behavioral context beyond that by calling the estimate 'pedagogique', signalling that it is approximate/indicative rather than official, and by listing which cost components are 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?

One sentence carries the verb, resource, component list, scope, and caveat with no filler. The key action and object are front-loaded, and the pedagogical caveat is placed at the end.

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 simple two-parameter, read-only estimator, the description is complete: it names the target, scope, included components, and the approximate nature of the result. The absence of an output schema is not a blocker because the return shape is obvious from the domain.

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 0%, so the description must compensate. It maps type_bien to 'ancien ou neuf' and implies that prix is the purchase price used for the estimate, but it never explicitly defines prix or its unit/currency, leaving some inference to the agent.

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 opens with the specific verb 'Estime' and names the resource 'frais de notaire', then enumerates the components (droits de mutation, emoluments, formalites) and scopes the tool to 'un achat ancien ou neuf'. This makes it immediately distinguishable from the sibling simuler_rendement_locatif, which estimates rental yield.

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?

It clearly states the intended context: notary-fee estimation for old or new purchases. It does not explicitly name exclusion conditions or route to alternatives, so it falls short of a full when/when-not explanation, but the use case is unambiguous.

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