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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds meaningful context beyond that, namely that the payload is reused and a NEW attempt is created rather than mutating the original record. It also discloses the concrete auth requirement and the exact recovery flow (authenticate via /mcp, then re-call), plus the notable nuance that start_login does not satisfy it. It omits idempotency/rate-limit behavior, keeping it short of a 5.

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 core purpose is front-loaded in the first sentence and the second sentence adds genuinely useful mechanism detail. The auth paragraph is slightly bulky but operational and earns its space for an unauthenticated agent.

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?

For a one-parameter mutation with no output schema, the description covers what it does, what it produces (a new attempt with the same payload), and how to satisfy auth. Nothing critical is missing, though stating whether the retry can be repeated or what response to expect would fully close the loop.

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 there is a single required 'id' param already documented in the schema as 'Webhook delivery ID to retry'. The description adds no syntax, format, or lookup guidance beyond that, so the schema does the heavy lifting and the baseline of 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 (Retry) plus resource (webhook delivery) and clarifies the mechanism: a new delivery attempt with the same payload to the configured endpoint. This clearly distinguishes it from siblings like get_webhook_delivery, list_webhook_deliveries, and get_webhook_stats.

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 phrase 'Retry a failed webhook delivery' implies the precondition (the delivery must have failed), which is useful. However, no alternative is named (e.g., re-sending via a different tool) and no exclusions are given, such as what to do if the delivery already succeeded or is still in flight.

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