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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds the important implication that this is a full replacement of the configuration (omitted fields are effectively lost), which explains the destructive flag, but it says nothing about permissions, side effects on deliveries, or what happens to the webhook secret.

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 short sentence that front-loads the mutable fields and appends the full-config requirement — no filler. It loses a point for being written in French while the entire tool surface and all sibling names are English, and for omitting the resource noun.

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 destructive update over an opaque nested config object with no output schema and no schema descriptions, the definition is only partially sufficient: it enumerates some config keys and states full-replacement semantics, but leaves the shape of the config object and the failure/validation behavior undocumented.

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% and the config parameter is an open nested object with additionalProperties {}, so the description carries the burden of documenting it. Naming five config keys (mapping, tags, campaign, origins, enabled) adds genuine meaning, but there are no types, nesting details, or indication of which keys are optional or required.

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 names the mutation targets (mapping, tags, campaign, origins, enabled) but never states the resource itself — 'webhook' appears only in the name and title. It also does not distinguish this tool from siblings such as create_form_webhook, delete_form_webhook, rotate_form_webhook_secret or preview_form_mapping.

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?

'fournir la configuration complète' implies the caller must supply the whole config rather than a patch, which is a real usage constraint. However, there is no statement of when to use this versus create/delete/rotate siblings, no prerequisite that the webhook id must already exist, and no mention of the separate secret-rotation tool.

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