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

Adds important behavior beyond annotations: nothing is charged again, and the corrected input path is only for the input_refused case. Annotations already cover read-only/destructive/idempotency, but the description does not describe what happens after a successful redelivery or any rate limits.

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 compact sentences, front-loaded with the main action and immediately followed by the critical financial reassurance and conditional input guidance. No wasted text.

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 two-parameter mutation tool with no output schema, this covers the key scenarios and the nested input correction path. It could be slightly more complete about post-redelivery outcomes, but an agent has enough to call it correctly.

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 coverage is 100%, so baseline is 3. The description adds meaningful context for the optional input parameter by tying it to delivery.input_refused and explaining it is the corrected version of the original input.

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 action and object: retry a paid order whose delivery failed. The parenthetical '(buyer or seller)' clarifies scope, and the verb 'retry' distinguishes it from initial purchase tools like buy.

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?

Gives a clear condition for use: orders whose delivery failed, and a specific sub-case for the optional input when delivery.input_refused. It does not explicitly name alternatives or exclusions, but the context is sufficiently clear.

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