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

Annotations already establish non-read-only, non-destructive, closed-world behavior. The description adds genuine context beyond them: the submission is time-boxed to 7 days and kicks off a review-and-refund process. It stops short of stating permissions, idempotency, or what happens if the window has elapsed, so it remains partial for a mutation.

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 immediately carrying the deadline and outcome. Nothing is redundant, but the brevity is achieved by omitting content rather than by efficient phrasing.

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 six-parameter mutation with no output schema and no parameter documentation anywhere, one sentence is not enough. The agent knows why to report but not what to put in five required fields or what it gets back.

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% across six parameters, five of them required, and the field names are opaque ("check", "truth", "record_id", "request_id"). The description does not explain a single one of them, leaving the agent to guess what "check" versus "truth" should contain, which is exactly the case where the description needed to compensate.

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?

"Reports a wrong charged result in a list" gives a specific verb and resource, plus the 7-day window and refund intent. It is clearer than the title ("Report a result in a list") and does not need a sibling name to be understood, though it never distinguishes itself from adjacent claims/refund tools like create_capacity_refund_claim.

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 7-day deadline implies a precondition for use and hints at urgency, which is real guidance. However, it never says when NOT to use it, nor which sibling to reach for instead (e.g., a capacity refund claim vs. this report), so the agent must infer alternatives from the sibling list alone.

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