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

Annotations only declare destructiveHint=true; the description goes further by explaining that rotateSecret invalidates the old secret ('the old one stops verifying') and returns the new one a single time, and that toggling enabled resumes outbound event delivery. Those are precisely the consequences an agent cannot infer from the schema or hints. The outbound-delivery wording sits slightly at odds with openWorldHint=false, but it describes the webhook's own runtime behavior rather than an unbounded tool domain, so it is not a genuine contradiction.

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?

Two sentences, front-loaded with the verb and resource, then the parameters in the order they matter. Every clause carries distinct information; none of it repeats the schema or annotations.

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 mutation with no output schema, it covers the dangerous paths well (secret rotation, enable gate, preview fallback). The notable gap is whether passing events replaces the existing subscription list or merges with it, plus permission requirements — either would matter before an agent calls it.

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 only 20% (only confirm is documented), so the description must carry the load, and it does: events = which event types it sends, enabled = off/on toggle, rotateSecret = secret replacement with one-time return of the new value, confirm = preview gate. Only webhookId is left implicit, and its meaning is self-evident from the sentence.

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 ('Changes one of the account's webhooks') and enumerates the three mutation surfaces: event subscriptions, enabled state, and signing secret. The verb 'changes' plus the required webhookId makes it unambiguous against create_webhook, delete_webhook, and list_webhooks without needing to open any 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?

Gives a concrete operational rule: enabling requires confirm: true because 'events leave Decknote again', and without it the call only previews. That is real guidance for the riskiest branch, but there is no explicit statement about when to prefer this over siblings (e.g., create/delete) or who is allowed to call it.

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