ocr_image

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

Annotations already declare readOnly/openWorld=false, and the description adds real value beyond them: output is paginated in parts and 'next_offset' is the cursor to feed back, plus 'lang' overrides the LATHE_OCR_LANG environment variable. It doesn't say what happens on unsupported formats or empty text, and the pagination pointer depends on an output field the agent must infer.

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?

Two short sentences, core purpose first, then the pagination mechanic and the language override. Nothing is wasted.

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?

An output schema exists, so return values needn't be explained, and the description covers the trickiest behavior (pagination). The only real gap is max_chars, whose truncation semantics are left silent.

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 description coverage is 0%, so the description must carry the load. It explains offset (as the continuation cursor) and lang (as an env-var override), but leaves max_chars and input_path entirely unexplained.

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 and resource: 'Extract the text from an image with OCR'. That uniquely separates it from pdf_extract_text and the info/resize/convert siblings, though it never names an alternative explicitly.

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 continuation rule ('pass next_offset as offset to continue') is a concrete usage instruction, but there is no guidance on when to pick this over pdf_extract_text or when OCR is inappropriate.

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