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

Beyond the read-only annotations, the description discloses the paid nature of the call ($0.009 USDC via x402 on named chains), how payment is settled inside the call, format/size limits (10 MB decoded, listed formats), and the return shape (text + 0-100 confidence). These are material traits the annotations do not carry.

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-loads the core purpose and then adds limits, returns, languages, use cases, and pricing in a readable progression. The pricing and 'free sample' sentences are slightly promotional but still carry actionable information.

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 supplies the return contract (text + confidence with an interpretive threshold), the input constraints, and the payment requirement — enough for an agent to invoke and interpret results 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% and the schema's own language/psm descriptions are actually more complete than the description (the description lists a subset of supported language codes). The description adds little beyond the schema, so the baseline 3 is appropriate.

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+resource ('Extract text from images') plus the engine (Tesseract OCR), which cleanly separates it from siblings like image_alt_text, barcode, or pdf_extract. An agent can identify the tool's function 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?

Gives concrete use cases ('invoices, receipts, scanned documents, or screenshots with text'), which tells the agent when this is appropriate. It does not, however, explicitly route against the closest siblings (pdf_extract, image_alt_text) or state exclusions, so it stops short of full when/when-not guidance.

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