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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real value beyond them: a hard cap of the last 20 attempts and the fact that the destination address is masked to host only — both behavioral traits an agent would otherwise not know.

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?

Three short sentences, each doing distinct work: what is returned, the diagnostic use case, and the address-masking caveat. Front-loaded with the return shape and no 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?

With no output schema, the description correctly carries the burden of describing the return payload (the delivery-attempt fields) and its 20-item limit. Combined with full schema coverage and annotations, an agent has enough to call and interpret it, though pagination or what happens when there are zero deliveries is unstated.

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 100% and each parameter (site_id, webhook_id, user_goal) is documented with its source tool in the schema. The description only implies webhook_id via 'One webhook' and adds nothing about site scoping or the optional user_goal, so baseline 3 applies.

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 with scope: 'One webhook with its last 20 delivery attempts', then enumerates the returned fields (event, success/failure, status code, timestamp). This clearly distinguishes it from list_webhooks (many webhooks) and test_webhook (triggers a send), though neither sibling is named explicitly.

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?

Provides a concrete diagnostic scenario: 'Use it to answer "why isn't my automation getting leads?"', which tells the agent this is the troubleshooting path for failed deliveries. It stops short of explicit when-not guidance or naming test_webhook as the alternative for actively firing a delivery.

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