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

The annotations already indicate read-only, non-destructive, and idempotent behavior. The description adds extra behavioral context by listing specific error scenarios (e.g., amount off by factor of 100, missing tax, invalid date format) and explaining that the API may return 201 with empty warnings when there are no issues. This goes beyond the annotation hints without contradicting them.

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?

The description is overly verbose, with lengthy enumerations of error cases and repetitive phrasing (e.g., multiple clauses about mismatches). It is not front-loaded; while the first sentence states the core action, the subsequent details drag on and could be streamlined. A more concise version would improve clarity and maintainability.

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?

The description covers a wide range of potential mismatches and even mentions a specific HTTP status code (201), but it omits a clear description of the tool's return value or output format. Since there is no output schema, specifying whether it returns a list, a boolean, or a report would be important for completeness. The description is partially complete but leaves this key aspect ambiguous.

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 includes descriptions for both parameters, so coverage is high. The tool description reinforces the meaning by referring to them as 'the body you sent' and 'the payment the API returned,' clarifying the expected roles. It does not add new constraints but provides useful context that ties the parameters to the comparison logic.

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 clearly states the tool's purpose: comparing the payment response against the request body and reporting mismatches. It also distinguishes this check from others by noting that it focuses on the response side, unlike other checks that focus on what is sent.

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 provides explicit guidance on when to use the tool: 'Run it after every createPayment while you are building, and in your own tests afterwards.' It also differentiates from sibling tools by explaining that other checks look at what you SEND, while this one checks the response for errors that survive.

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