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

The description is behaviorally rich, warning that a successful OCR call debits 1 credit, exposing credits_burned and credits_remaining, and describing error and retry semantics. However, it directly contradicts the readOnlyHint=true annotation by describing a state-changing side effect (credit.debit reason=ocr_success), which forces a score of 1 per the rubric.

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 front-loaded with the operation and packs setup, auth, cost, success, and error handling into a dense block. It is efficient overall, though the single run-on format and slightly redundant retryable/next phrasing keep it from a top score.

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?

Given no output schema, the description covers the essential lifecycle: install, auth, quoting, credit cost, response fields, and error mapping. The main omission is the shape of the successful OCR payload beyond the credit fields, but the golden URL and llms.txt reference partially cover verification.

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 sole url parameter already documents the absolute http(s) requirement. The description repeats the golden URL but adds no significant new parameter semantics beyond providing a test value, so it earns the baseline score.

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 'Image OCR (POST /ocr)' and the title states 'OCR image URL to plain text', giving a specific verb, resource, and transformation. This cleanly differentiates it from the sibling credit and key-management tools.

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 gives concrete preconditions: prefer Authorization Bearer over X-API-Key, quote first with quote_credits before the OCR call, and handle 401/402/retryable failures via next. It provides clear context and workflow, though it does not explicitly name an alternative OCR tool or state when not to use it; since the siblings are all non-OCR operations, this is adequate.

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