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

While annotations already declare destructiveHint=true and idempotentHint=true, the description adds material behavior: 'Do not redirect notifications without the operator's authorization', 'Agent/environment scope cannot be changed', and the idempotency retry instruction. These go beyond the annotations and help an agent avoid unauthorized or dangerous side effects.

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 dense sentences, each carrying a distinct fact: the update verb, the authorization caveat, the scope limitation plus auth model, and the idempotency instruction plus a docs link. No filler words and the primary action is front-loaded.

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?

The description covers the action, permission requirement, scope limits, idempotent retry behavior, and points to documentation. With an output schema present and a detailed input schema, this is enough for a competent agent, though openWorldHint=true leaves room for additional undisclosed side effects that the description does not enumerate.

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 description maps top-level parameters to business concepts ('URL, events, keyword rules', 'active/paused status'), but with 0% schema coverage it does not explain the nested rules structure (match, source, terms, exclude_terms) or precisely how expected_revision governs the update. It partially compensates for the absence of schema descriptions but leaves several parameters under-explained.

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 opens with a specific verb and resource — 'Update name, URL, events, keyword rules or active/paused status with expected_revision' — and enumerates the mutable fields. It clearly identifies this as a mutation of an existing endpoint, distinguishing it from create/test tools, though it does not explicitly contrast with the sibling update_webhook.

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?

The description provides concrete operational guidance: 'Requires webhook.manage', 'Uses the same bounded control plane and tenant/agent/Live-Sandbox authorization', and warns against redirecting notifications without operator authorization. It also gives retry guidance — 'Reuse the exact idempotency_key and input after an uncertain mutation' — though it stops short of explicitly naming alternatives when to use them.

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