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

Annotations already declare the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the bar is lower. The description usefully discloses that confidence is returned both overall and per field, but says nothing about processing time, failure modes on unreadable scans, rate limits, or whether repeated calls are safe.

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 the action and output shape front-loaded, then the input mechanics. The long field enumeration is lengthy but earns its place because there is no output schema backing it.

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 burden of describing the return payload, and it does so in detail. The remaining gap is that all four parameters are optional and the description never says what happens if no file is supplied, or which of the three channels takes precedence.

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 both the three file channels and file_name are already documented in the schema. The description's mention of file_url/file_base64/file merely restates the schema's own descriptions in condensed form rather than adding format or precedence rules. 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?

"Extract an invoice's data as structured JSON" gives a specific verb and resource, and the enumerated field list (vendor, invoice number, tax lines, line items, confidence) makes the output concretely imaginable. It does not name or contrast against siblings like check_invoice or invoice_to_excel, so an agent must infer the routing from the field list alone.

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?

"Give the file as file_url, file_base64 or (ChatGPT) file" is genuine input-channel guidance. However, there is no statement of when to pick this tool over check_invoice (validation) or invoice_to_excel (spreadsheet conversion), and no prerequisites or exclusions are given.

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