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

No annotations are present, so the description carries the full burden. It discloses important behavioral traits: idempotency, lack of judgment rerunning, and refusal to resend completed/cancelled requests. This goes well beyond a generic retry tool, though it omits details like authentication requirements or what happens on a nonexistent request_id.

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?

Two tightly written sentences carry all essential information. The main action is front-loaded, followed by idempotency behavior and the critical precondition. No wasted words or redundancy.

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 tool with two parameters, no output schema, and no annotations, the description covers purpose, usage, idempotency, and exclusions. It is nearly complete, but a brief note on failure behavior or response shape would fully round it out given the lack of an output schema.

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%, so the schema already documents both parameters fully. The description adds no parameter-specific detail beyond referring to 'the same saved message,' which does not meaningfully enrich request_id or connection semantics. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Resume a saved pending delivery after a network failure or restart.' It also clarifies the action by saying it sends the same saved message idempotently and without rerunning judgment, which clearly distinguishes it from inspection or creation tools like request_get and request_create.

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 description gives explicit when-to-use context ('after a network failure or restart') and a clear when-not-to-use rule ('completed or cancelled requests are never resent'). It also instructs the agent to inspect request_get first, providing a concrete prerequisite and routing implied by that alternative.

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