Extract text from images (OCR)

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

Annotations already mark readOnlyHint=true, but the description adds substantial behavior beyond that: it runs an Apify actor, requires APIFY_TOKEN, has per-page billing, enforces a spending cap, and treats PDFs with text layers differently. It even notes failed downloads and empty pages are free. No contradiction with annotations; this is rich, honest disclosure.

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 long but densely informative, front-loaded with the core function before cost and backend details. Every sentence earns its place—formats, languages, alternatives, billing, and token usage are all relevant. It is structured logically, though a touch verbose for agents that prefer brevity.

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 explains the return value ('reading-order text per image or PDF page with an average confidence, and optionally every line with its pixel bounding box'). It covers cost, failure cases, input limits, and batching advice, making it fully sufficient for an agent to call the tool correctly.

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 each parameter has a basic description. The tool description adds meaningful context: it ties quality to cost, explains that each image/PDF page is one charged result, clarifies pdfMode behavior, and warns about output size for includeLines. This goes beyond the schema without duplicating it, though it doesn't explicitly walk through every parameter.

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 opens with a precise verb ('extract the text'), a clear resource (images, screenshots, photos, scanned PDFs), and the exact return (reading-order text with confidence, optional bounding boxes). It also names the sibling it is not ('For digital (non-scanned) PDFs and Office files prefer convert_document_to_markdown'), so an agent can distinguish it from similar tools immediately.

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 states when to use it ('receipts, invoices, forms, scanned documents, screenshots and product photos') and when not to ('digital (non-scanned) PDFs and Office files'), naming the alternative tool. It also adds practical guidance on cost and batching, leaving no ambiguity about selection.

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