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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so safety is partly covered. The description adds substantial non-obvious behavior: 10MB size limit, no server-side storage of the file, a mandatory email, a 5-per-email-per-day quota, and a prompt-injection caveat that extracted values are data not instructions. The quota is the only trait left ambiguous (per calendar day vs rolling window).

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?

Front-loaded with the core action and return payload, then constraints and caveats. It is a single dense paragraph rather than a run-on of filler, though the email/quota and injection caveats could be split for scannability.

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?

There is no output schema, so the description compensates by enumerating the extracted fields, and it also covers input limits, auth (email), quota, and data-handling policy. For a single-shot extraction tool with one required parameter, 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 the baseline is 3, but the description adds real meaning: it explains the email parameter's purpose (required, and used for both quota tracking and tool updates) and the mutual exclusivity/constraint on the URL versus the ChatGPT-attached file. It does not clarify the nested file object's file_id/download_url split, which the schema carries.

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 (Extract) and resource (purchase order), enumerates exactly what is returned (PO number, dates, buyer/vendor, currency, terms, totals, line items with SKU/qty/price), and scopes the input formats (PDF or image). An agent can distinguish this from parse_invoice or match_po_to_invoice without opening any 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?

Gives clear preconditions for use: the URL must download the file directly without a login, and the file may alternatively be attached in ChatGPT. It does not explicitly name an alternative or state when not to use it (e.g., use match_po_to_invoice once the PO is parsed), so it falls short of full routing guidance.

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