manage_webhook

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

Annotations declare destructive/openWorld/non-idempotent, but the description adds what those hints cannot: that updates have outbound side effects, that delete is a two-phase preview/confirm flow requiring the returned preview_id, and that test dispatches a signed webhook.test delivery. This is precisely the human-in-the-loop safety protocol an agent needs and could not infer from the structured fields.

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?

Efficiently segmented by action (update / delete / test) with the parenthetical webhook_id acting as a signature per branch, and the most important constraint (list first, confirm last) is front-loaded. Some clauses are dense run-ons, but no sentence is 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 9-parameter, three-mode destructive mutation with no output schema, the description covers every decision an agent must make: mode selection, which params apply per mode, the confirmation precondition, and the destructive preview flow. Nothing needed to invoke it correctly 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 the schema already labels url/events/is_active/description/workspace_id as "update only" and documents confirm and preview_id. The description still adds cross-parameter meaning the schema fragments cannot — namely that preview_id only exists as the output of a prior no-confirm delete call, and that it must be paired with confirm=true. Slight redundancy with the confirm field text keeps it from a 5.

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?

Opens with a specific verb+resource ("Change a webhook subscription") and immediately scopes itself against the sibling list_webhooks. Each of the three action modes is then named with its required identifier, so an agent can tell this apart from create_webhook and list_webhooks without opening 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?

Explicit routing guidance: "list them first with list_webhooks" before acting. Per-action conditions are spelled out — update for field changes, delete requires preview-then-confirm with a preview_id, test is for sending a signed sample delivery — and each says when confirm=true is permitted ("only after explicit confirmation").

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