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

Annotations already establish that this is a non-destructive, non-open-world write, so the description only needs to add context. It does add one genuinely valuable fact — "Secret et URL retournés une fois" — warning that the credential is not retrievable later, plus the constraint that browser mode requires exact origins. It says nothing about permissions, failure modes, or what the created webhook looks like.

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?

Four short fragments, front-loaded with the verb and resource, with no filler. The telegraphic styling and mixed French/English phrasing make some clauses ("mapping destination→chemin source") require re-reading rather than being immediately parsed.

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 creation tool whose only input is an untyped nested object and which has no output schema, the description should document the config shape and at least gesture at the return payload. Instead it gives four fragments, leaving the agent unable to call the tool without trial and error.

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?

The single `config` parameter is a free-form object with no property definitions and 0% schema description coverage, so the description carries the full burden. It offers only scattered hints (destination→source path mapping, required email, exact origins in browser mode) and never enumerates the accepted config keys, so an agent cannot construct a valid payload from this text.

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 ("Créer un webhook de formulaire") plus the platform scope (WordPress/HTML/React), which separates it from siblings like update_form_webhook, delete_form_webhook or describe_form_webhooks. It stops short of explicitly naming those siblings, so an agent must infer the boundary from the name alone.

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?

There is no when-to-use guidance: nothing says to run preview_form_mapping first, to call list_form_webhooks to check for an existing webhook, or how this differs from update_form_webhook. The fragments about mapping and browser mode are configuration facts, not selection guidance.

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