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

The destructiveHint annotation already signals mutation. The description adds valuable behavioral context: seller vs. buyer permissions, full refund including platform fee, and the caveat about quality disputes. This goes beyond annotations but doesn't exhaustively describe consequences like irreversibility, which is acceptable since annotations cover the safety profile.

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?

Three dense sentences, each earning its place: the core action, differentiated role rules, and an alternative path. Starts with the verb immediately and delivers maximum information in minimal words.

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?

Given the destructive nature, the description provides sufficient context: role-specific conditions, how to check eligibility, what the buyer receives, and when to use an alternative tool. No output schema exists but return format is less critical for a mutation tool; the description covers the decision-making needs well.

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?

The schema covers reason well ('Why, max 600 characters. Shown to the other side.') but charge_id lacks description at 50% coverage. The description indirectly explains charge_id by advising 'call charge_get to see due_at and overdue,' implying how to obtain the charge identifier. It adds some context but doesn't explicitly define the parameter format or required value.

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+resource: 'Send the money back on a charge.' It clearly distinguishes the tool from siblings by explaining seller vs. buyer refund conditions and explicitly contrasts with submit_feedback for quality disputes.

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?

Provides explicit when-to-use instructions: sellers can refund any charge, buyers only undelivered charges past due, and directs to charge_get for verifying eligibility. Also names the alternative submit_feedback with type dispute for quality issues, making the usage boundaries clear.

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