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

Annotations already declare readOnly/idempotent/non-destructive, so 'Read only' is largely redundant, but the description adds genuinely new behavior: results are 'recent' and paginated, which the annotations do not convey. It still doesn't state a default page size or how far back 'recent' reaches.

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, front-loaded sentences with no filler; scope, follow-up action and pagination status are each stated once and immediately.

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?

No output schema exists, so the field enumeration (event, status, attempts, response code, when) usefully describes the payload shape. Pagination is noted, but the undocumented page/limit parameters leave a small gap for a 4-param tool.

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 only 25% — page, limit and webhookId are undocumented in the schema, and the description lists return fields rather than explaining these inputs. With low coverage the description was expected to compensate and does not.

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 — 'Recent deliveries for one webhook' — and the parenthetical enumerates the returned columns (event, status, attempts, response code, when). This clearly separates it from list_webhooks (which enumerates webhooks) and from create/update/delete_webhook siblings.

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?

Explicitly routes failed deliveries to retry_webhook_delivery, giving the agent a concrete follow-up action. It lacks an explicit when-not statement (e.g. how it differs from list_webhooks for a bulk view), so it falls short of 5.

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