ocr

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

With readOnlyHint=true already covering safety, the description adds valuable behavioral detail: it returns lines with confidence and boxes in screenshot pixels, and it reports a ~0.7 s latency for a full 1080p screen. This is useful operational context beyond the annotations, and there is no contradiction.

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?

Three short sentences deliver the core action, output format, usage guidance, and performance expectation with no filler. The main purpose is front-loaded, and 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?

Despite having no output schema, the description adequately covers the return format (lines, confidence, boxes in screenshot pixels), the usage context, and expected latency. The schema handles parameter details, and the annotations handle safety, so nothing critical is missing for an agent to select and invoke this tool 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 description coverage is 100%: both `lang` and `region` are already documented with meaningful examples and coordinate semantics. The description adds no additional parameter-level meaning beyond reinforcing the screenshot-pixel context, so the high-coverage baseline of 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?

The description opens with a specific verb and resource, 'Read text from the screen with tesseract', and clarifies the output shape ('lines with confidence and boxes in screenshot pixels'). It also scopes the tool to cases where accessibility has nothing, helping distinguish it from sibling screen-reading alternatives.

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?

It explicitly states when to use the tool: 'Use when accessibility has nothing', with concrete examples like images, canvases, terminals, and remote desktops. It does not explicitly name alternative sibling tools or state exclusion criteria, so it stops short of a 5.

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