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

With no annotations, the description carries the full burden and does disclose two useful behaviors: this is a re-send mutation, and it resets the attempt counter to 0 rather than continuing the backoff. It also hints at authorization (owner or office). It does not state whether a new delivery record is created or the existing one is mutated, whether the original attempt history is preserved, or what the result looks like.

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?

One sentence, front-loaded with the action and the attempt-0 behavior. Efficient, but the parenthetical "(owner or office)" is ambiguous shorthand that costs more confusion than the character savings justify.

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 an annotated-free mutation with no output schema and 0% parameter coverage, the description should explain the return value (new attempt? delivery status?) and how to source the delivery_id. Neither is present, leaving an agent unable to predict the outcome of the call.

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% and the description never mentions delivery_id — neither its format (integer id) nor where an agent obtains it. The retry semantics are explained, but the single required parameter is left entirely undocumented by both description and schema.

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 object: re-send a failed or dead delivery, and adds the meaningful detail that it restarts from attempt 0. An agent can tell this is a retry action, though the description never names the related webhooks_deliveries/webhooks_list tools that surface the delivery to retry.

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 "failed or dead delivery" implies the triggering condition, and "(owner or office)" signals a role restriction. However, there is no explicit statement of when not to use it, no pointer to the tool that produces the delivery_id, and no guidance on what to do after repeated failures.

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