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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description usefully narrows the side-effect profile by naming two things that will not happen (no contact created, no campaign launched). However it says nothing about what the preview actually returns or why destructiveHint is set to true, leaving a real inconsistency in the safety story unexplained.

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 with no filler; the non-destructive condition is placed correctly after the action. It is short, though it is written in French while the tool name, title and all siblings are in English, which is a small consistency cost.

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, zero schema description coverage, and a nested free-form object parameter, so the description needed to explain the expected input shape and what the preview returns. It delivers neither, offering only a high-level intent.

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% for both required parameters, so the description carries the full burden and does not meet it. It never explains that 'id' identifies the form and that 'fields' is a nested sample payload, nor what shape that nested object should take.

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 specific verb and object ('Tester le mapping' with 'un exemple de formulaire'), so an agent knows this is a dry-run of a form field mapping. It does not reference any sibling tool (e.g. list_forms, describe_forms, update_form_webhook) to distinguish itself, and 'mapping' is left as unqualified jargon.

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: the 'sans créer de contact ni lancer de campagne' clause suggests this is the safe check to run before the real operation, which is useful. But there is no explicit when-to-use rule, no prerequisites, and no named alternative for the opposite case (applying/committing the mapping).

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