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

The description discloses high-value behavior that the annotations do not: a 1-credit cost with a refund when the file is unreadable, and an implicit persistence/duplicate-detection side effect (consistent with readOnlyHint=false). It also tells the agent the result includes reasons for AI/edit scoring.

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 core capability is front-loaded in one dense but well-structured sentence, with cost/refund as a distinct second sentence. It is long, but nearly every clause maps to a real user-visible behavior, so little is wasted.

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 tool with an output schema, return values need not be explained; the description instead covers the input modes, billing, refund condition, duplicate check, and detection scoring. Nothing an agent needs to invoke it correctly is missing.

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 parameter (api_key, image_url, mime_type, image_base64) is already documented and the baseline is 3. The description only restates the URL-vs-base64 duality and file types, adding no syntax or constraint detail beyond the schema.

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 states a specific verb-and-resource with enumerated sub-operations: extract fields, check arithmetic/tax/dates, score edit/AI-generation signals, and duplicate-submission lookup. An agent can distinguish this from every sibling (create_api_key, create_claim_link, get_account, report_feedback) without opening a schema.

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?

It gives clear triggering context (receipt/invoice verification) and acceptable inputs (image or PDF, https URL or base64), which frames when the tool applies. It does not name exclusions or alternative tools, but the sibling set is unrelated, so there is little genuine ambiguity to resolve.

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