computer

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotent, so the safety profile is partly covered. The description adds genuine behavioral context: coordinates default to image-space pixels and are scaled to the screen, space:"screen" uses unscaled reported positions (with a macOS point-vs-pixel caveat), and the expect parameter returns a DEVIATION on failed post-conditions requiring adaptation. It does not restate the destructive nature, but the added coordinate and verification semantics are substantive.

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?

Front-loaded with the core purpose, then the action enum, then routing guidance, so the most important selection signal (prefer accessibility) lands early. The long action enumeration is dense but earns its place by defining the dispatch surface. Minor redundancy in restating the enum, but no wasted prose.

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 23-parameter, multi-action tool with no output schema, the description covers dispatch, coordinate spaces, sibling routing, and post-condition verification. Annotations carry the safety profile. The one gap is that individual action-to-parameter mappings (which params apply to which of the 23 actions) rely entirely on the schema, but the overall behavioral envelope is well specified.

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 100%, so the baseline is 3, but the description adds cross-cutting meaning the schema alone does not: the default coordinate space is image-space scaled from the latest screenshot, and pass space:"screen" to click positions reported by accessibility. This resolves the ambiguity of how x/y map between capture and screen, which is the highest-risk semantic in the tool.

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 family and resource ('Direct mouse/keyboard/screenshot control') and enumerates the full set of sub-actions, so an agent knows exactly what capability this covers. It explicitly differentiates itself from siblings by naming accessibility and system as the preferred alternatives for named targets and text. No other sibling tool overlaps this pixel-level control scope.

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?

Gives explicit when-to-use and when-not-to-use guidance: screenshot is the LAST RESORT, first try accessibility read_tree/find/compile_ui or system copy_all_text, prefer accessibility for named targets, and use computer only for pixel-level control. It names the alternative siblings and the condition that selects each, leaving nothing to inference.

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