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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is largely covered. The description adds genuinely useful behavioral context beyond that: it discloses the return shape ('a one-line verdict and every problem found, with the invoice's own numbers'), which matters because there is no output schema. It does not explain the non-read-only flag or any limits on file size/download fidelity.

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 sentences with no filler: the first front-loads the four specific checks, the second covers return value and accepted input forms. Every clause carries information the agent needs.

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?

Because no output schema exists, the description correctly compensates by summarizing the verdict and problem list, and it enumerates all input channels. It stops short of error/failure behavior, unsupported document types, or any note on why the call is not marked read-only, which leaves a small but real gap for a file-ingesting tool.

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 each of the four file parameters is already documented (including the ChatGPT-only file object and the base64 option). The description only restates the three input channels ('file_url, file_base64 or (ChatGPT) file') and adds no format, size, or precedence detail beyond the schema, so the baseline 3 applies.

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 verb (check) and resource (invoice) and enumerates the exact arithmetic verifications performed: line quantity times unit price, lines vs subtotal, tax vs printed rate, subtotal plus tax vs total. This is precise enough to separate it from siblings extract_invoice_data (extraction) and invoice_to_excel (conversion), which do not mention arithmetic validation.

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?

Usage is implied by the enumerated checks and the sibling set, but the description never states when to pick this tool over alternatives such as extract_invoice_data, nor does it mention prerequisites (e.g., needing a machine-readable invoice before checking). The closing sentence about input forms is parameter guidance, not usage routing.

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