page_ocr

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

With no annotations, the description carries the behavioral burden and does well: it discloses that processing is '100% local', that models auto-download to GHOSTFOX_HOME/models, and that first call downloads ~12MB. It does not mention return format or failure behavior, but the core operational traits are covered.

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 compact and front-loaded with the key action. There is slight redundancy between 'auto-download once to GHOSTFOX_HOME/models' and 'Models download on first call (~12MB, once)', which costs a point, but overall every sentence earns its place.

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?

For a tool with no output schema and no annotations, the description covers purpose, scope, local execution, and the download side effect. It stops short of specifying the return value format or error cases, which an agent might need, but the information required to select and invoke the tool is largely present.

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 only 33%: only 'ref' has a description. The tool description reinforces the ref semantics ('or the whole viewport if no ref') but does not add new meaning for 'session_id' or 'page_id'. These are standard context parameters, so the gap is minor, but the description does not fully compensate for the low schema coverage.

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 clearly states the action: 'extract text from an element (or the whole viewport if no ref)'. It also names concrete use cases ('image captchas, canvas text, scanned UI'). However, it does not explicitly differentiate from sibling tools like page_captcha_ocr or page_vision, so the boundary is implied rather than stated.

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 clear when-to-use context: 'Answers "what text is written there"' and lists typical OCR scenarios. It does not provide explicit when-not-to-use guidance or name alternatives, but the intended use is evident from the phrasing and the 'LOCAL OCR' label.

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