desktop_ocr

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

The description goes well beyond the readOnly annotation by disclosing that no input is sent, results are local candidates with uncalibrated scores, the snapshot expires after 15 seconds or eviction, and changed layouts cause refusal. These are meaningful behavioral details an agent must know before calling the tool.

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?

Four dense sentences, each earning its place: purpose, return semantics, validity constraints, prerequisites/privacy. The most decision-relevant information is front-loaded, and there is no repetition of schema or annotation data.

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 read-only tool with no output schema, the description fully covers what is returned, what is not returned, when the call can fail, prerequisites, and privacy behavior. The only minor omission is limit semantics, but that is a small parameter detail and does not undermine safe invocation.

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 compensate. It does clarify snapshot_id as the exact retained screenshot and language as the selected installed language, but it never explains the limit parameter or its default behavior. The compensation is partial at best.

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 uncertain local OCR word candidates from this exact retained screenshot.' It actively distinguishes itself from any capture-based or exact-text tool by saying 'never a new capture' and 'not exact text or action permission,' making it easy to tell apart from siblings like desktop_read_text or desktop_observe.

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 gives clear conditions: use on the retained snapshot, not a new capture; the snapshot must still be valid and unchanged; Tesseract and the selected language must be installed. It implies exclusions by saying this is not exact text or action permission, though it does not explicitly name alternative sibling tools.

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