Inspect screen (vision)

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

With no annotations, the description must carry behavioral disclosure, and it does state what the tool returns (screenshot, UI tree, optional vision description) and that vision is opt-in. It omits whether the vision-model call adds latency/cost, whether the operation has side effects (it appears read-only but this is never stated), and permission requirements.

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?

A single front-loaded sentence that packs the key information with no filler. It is dense to the point of being terse — the optional/conditional nature of the vision description is the only nuance conveyed — but 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?

For a no-annotation, no-output-schema tool with a nested target object and two undocumented params, the description covers the return composition adequately. It remains incomplete on side-effect/permission posture and on the tree-depth and includeTree controls an agent would need to call it precisely.

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 50% and the nested target object is documented in-schema. The description usefully explains the 'focus' parameter as a vision-model topic instruction, but says nothing about includeTree or maxTreeDepth, leaving two parameters undocumented in both places.

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 ('Inspect screen') and enumerates the composite output: 'screenshot + UI tree, optionally with a vision-model description'. This distinguishes it from the bare computer_screenshot sibling by conveying it is a fuller, multi-source observation. It stops short of explicitly contrasting itself with computer_get_state or computer_locate.

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?

'Full observation' implies this is the superset call to reach for when a complete picture is needed, and the optional focus scopes it to a topic. However, no when-to-use vs when-not guidance is given and no alternative sibling (e.g., computer_screenshot for a quick capture, computer_get_state for non-visual state) is named.

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