retry

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the state transition (failed states → pending queue), but says nothing about permissions, whether the original attempt is preserved or duplicated, rate limits, or side effects — significant gaps for a mutation tool.

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?

A single tight sentence, front-loaded with the verb and target state. Nothing is wasted, though it is terse enough to leave real questions unanswered rather than being a model of completeness.

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?

An output schema exists, so return values need not be described. However, for a state-changing 3-parameter tool with 0% schema coverage, the undocumented not_before parameter and the lack of any authorization or side-effect context leave it only minimally complete.

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 message_id, recipient, or the not_before delay parameter. At 0% coverage the description should compensate, but it adds no meaning beyond the parameter names, leaving not_before (default 0) entirely unexplained.

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 gives a specific verb ('put back into the pending queue') and resource ('delivery'), and even enumerates the eligible source states (failed/needs_review/dead_letter), so the operation is unambiguous. It does not, however, differentiate itself from similar siblings like release or cancel.

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 implied by the enumerated precondition states — an agent can infer it applies only to deliveries in failed/needs_review/dead_letter. There is no explicit when-not guidance or comparison against the sibling tools that also manipulate delivery state.

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