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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds useful constraints: a 5MB image cap and 5s download timeout, plus the fact it uses a vision LLM. It redundantly states 'Read-only' but the added limits provide value beyond annotations.

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 description is two sentences with no filler. The core purpose is front-loaded, constraints are appended, and every word contributes to understanding the tool. It is appropriately concise without sacrificing critical details.

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?

The tool is fairly simple: takes an image and returns JSON. The description lists the extracted fields, so an agent knows what to expect. It includes size and timeout limits. It lacks explicit error-handling behavior, but given the annotations and the tool's read-only nature, it is largely complete.

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 coverage is 100%, so the schema already documents all three parameters. The description does not add new meaning beyond what the schema states, such as the requirement for one source or the optional nature of currencyHint. The baseline of 3 is appropriate given high schema coverage.

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 clearly states the tool parses receipts/invoices from images, specifies the input types (URL or base64), lists the extracted fields (merchant, total, VAT, date, currency, line items), and notes it uses a vision LLM. This distinguishes it from sibling tools like file_to_data_inspect or transcribe_and_slice_audio.

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?

The description implies the tool is for receipt/invoice images but does not explicitly state when to use it versus alternatives, nor when not to use it. It gives input constraints but no exclusion criteria or mention of other tools that might be more appropriate for different document types.

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