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

With no annotations, the description carries the full burden and does well: it discloses price ($0.20 per image), format and 5 MB size limits, payment mechanism (USDC on Base, no account/API key), and error behavior (no text found = 400, no charge). Rate limits and latency are not covered, keeping it short of a 5.

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?

Dense but front-loaded: purpose, cost, accepted inputs, workflow, error policy, and payment all land in four tight sentences with no filler. Every clause carries operational 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 annotations and no output schema, the description covers inputs, size limits, cost, payment, and failure semantics, which is nearly everything an agent needs to call it. Return-shape details (e.g., response field for the text) are only partially implied by 'exact text with line breaks preserved'.

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 four parameters. The description only restates the url-or-base64 choice already captured in the schema, adding no format or constraint detail beyond it — 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?

States a specific verb+resource: OCR over image inputs (scans, photos, screenshots) producing exact text with line breaks and reading order preserved. It implicitly separates itself from doc_extract/doc_to_markdown/media_transcribe by naming image formats, but never names a sibling explicitly, so an agent must infer the boundary.

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 workflow context ('one call: send a url or base64 — no upload step, no polling'), which implies when this tool is convenient. However it never states when to choose doc_ocr over doc_extract or doc_to_markdown, nor any exclusions, leaving usage implied rather than directed.

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