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

Beyond annotations, it discloses key behaviors: preserving event_id for deduplication, rechecking the current endpoint revision, requiring webhook.manage, and sharing a specific authorization model. It also clarifies negative behaviors, such as not replaying successful deliveries or approving facility handling.

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?

The description front-loads the core purpose and keeps every sentence purposeful, covering preconditions, exclusions, permissions, and idempotency guidance. It is slightly longer than strictly necessary, particularly the control-plane authorization sentence, but it avoids redundancy.

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?

Given four required parameters, an output schema, and annotations, the description is largely complete: it covers when to use it, what it does not do, permission requirements, and idempotency behavior. Minor ambiguity remains about failure semantics if the expected_revision does not match, but this does not block correct invocation.

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 0%, so the description must compensate. It indirectly explains expected_revision via 'rechecks the current endpoint revision' and idempotency_key via 'Reuse the exact idempotency_key and input after an uncertain mutation.' However, delivery_id and endpoint_id rely mostly on their self-explanatory names rather than explicit semantics.

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 uses a specific verb and resource: 'Explicitly retry a failed delivery after correcting the receiver.' It clearly distinguishes this from sibling tools like list_webhook_deliveries and test_webhook_endpoint by stating the exact action and its precondition.

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?

It gives clear context and explicit exclusions: retry only after correcting the receiver, do not replay successful deliveries, and do not approve facility handling. It also states the required permission and the idempotency-key reuse guidance, though it does not name a specific alternative tool.

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