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

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the bar is lower. The description nonetheless adds real behavioral context beyond them: newest-first ordering, that each row includes every attempt and the receiver's response, and that a pending delivery with next_attempt_at is being retried rather than lost. It also discloses the required webhooks:read scope, an auth detail no annotation covers.

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, front-loaded with the resource and ordering, then the retry semantics, then the scope requirement. Every clause carries information an agent needs; nothing is repeated from the schema.

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 usefully sketches the return payload (attempts and receiver answers) and explains the ambiguous pending state, plus the auth requirement. It omits any pagination or result-cap behavior beyond the schema's limit field, a minor gap for a read-only list.

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%, so limit, status, and endpoint_id are fully documented in the schema and the baseline is 3. The description adds only a semantic gloss on the ' pending' status meaning; it says nothing about the filters, ranges, or defaults that would deepen parameter understanding.

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 states the resource (recent webhook deliveries), the ordering (newest first), and the return shape (every attempt plus receiver's answer), which clearly separates it from list_webhook_events and list_webhook_endpoints. It never names a sibling explicitly, but the resource is specific enough for correct selection.

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?

Usage is only implied ('Recent webhook deliveries'), with no when-to-use statement, no exclusion criteria, and no pointer to the sibling list_webhook_events or list_webhook_endpoints tools. The note that pending deliveries carry next_attempt_at is helpful context but is not guidance on selecting this tool.

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