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

Goes beyond the annotations by disclosing the 60-minute validity window on download links, that no sign-in is required, and that re-submitting creates a new job (consistent with idempotentHint=false). It does not cover file size/format limits, processing latency, or failure behavior, so it is useful but not fully rounded out.

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 front-loaded sentences with the outcome stated first, followed by input options and the sibling routing hint. Dense but every clause carries information; only the parenthetical '(ChatGPT)' aside mildly duplicates the schema.

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?

With no output schema, the description correctly carries the return-value burden by naming header fields, line items, and the two download formats with their 60-minute lifetime. Missing only edge-case guidance (invalid file, failed extraction) for a full 5.

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 parameters already documents its purpose, including the ChatGPT-only file object and when to use base64 for local files. The description recaps the same three input routes without adding syntax, size limits, or precedence rules 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?

Specific verb and resource ('Read an invoice (PDF, scan or photo) and turn it into a spreadsheet') plus a concrete statement of what comes back: header fields, line items, and Excel/CSV download links. It also names the sibling get_result as the route for additional outputs, so the agent can separate it from the other invoice tools.

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?

Explicitly routes input formats by client ('file_url, file_base64 or (ChatGPT) file') and states a clear when-not condition: to get more outputs from an already processed invoice, use get_result with its job_id rather than resubmitting. It does not distinguish itself from check_invoice or extract_invoice_data, which is the remaining gap.

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