read_screen

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

The description discloses meaningful behavior beyond the readOnlyHint annotation: the output is a single line per element with specific fields, and it explains that 'positions=unresolved' still allows actions via refs. It also warns about the failure mode of non-accessible apps, which is valuable behavioral context.

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: it immediately defines the output format, then provides actionable usage guidance, then clarifies an edge-case state. Every sentence earns its place with no repetition of schema details.

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 there is no output schema, the description adequately documents the return format, coordinate system, semantics of unresolved positions, and limitations of the tool. It supplies enough context for an agent to call read_screen correctly and interpret its results.

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 75%, so the schema already explains scope, filter, ref_id, and max_chars well. The description adds context about refs being preferred over pixel coordinates, but does not add significant meaning to the parameters themselves. This aligns with the baseline for high 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 states a specific verb/resource ('Accessibility tree of windows') and precisely describes the output format, including refs, roles, names, boxes, values, states, and actions. It also distinguishes itself from screenshot/OCR-based tools by identifying when the accessibility tree is the right source.

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 explicit usage guidance: 'Prefer refs over pixel guessing' and directs the agent to use screenshots/OCR for apps that do not expose accessibility. This clearly helps select between read_screen and its siblings like ocr or computer.

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