Control computer

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds value by distinguishing observe-only operations from state-changing ones: 'Snapshot/find/wait operations observe state; clicks, typing, window close, app launch, clipboard writes, and recording can change local application state.' This is useful behavioral context beyond the annotations and is consistent with them.

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 sentences with no filler. The first sentence front-loads the tool's purpose and scope, the second adds critical behavioral nuance about which operations mutate state, and the third gives a targeting preference. 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?

For a tool with this much schema complexity and a rich output schema, the description is sufficiently complete: it defines the domain, separates read vs. mutate operations, and offers a targeting heuristic. It does not enumerate all supported operations, but the schema's operation enum and parameter definitions carry that burden. Minor gaps like platform-specific caveats are left to the schema.

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%, and the schema provides extremely detailed descriptions for every parameter, including nested objects and operation-specific constraints. The description itself adds little parameter-level detail, but with full schema coverage the baseline of 3 is appropriate; it does not need to compensate.

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 names a specific verb and resource: 'semantic inspection or control of native desktop applications on this computer.' It lists concrete capability categories (windows, accessibility/UI elements, app launch, clipboard, recording) that clearly distinguish it from sibling file/terminal/read tools. An agent can tell this is the desktop-automation tool without opening the schema.

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?

The description gives clear context for when to use the tool: 'Use this for semantic inspection or control of native desktop applications on this computer.' It also provides an important operational guideline, 'Prefer semantic targets before raw coordinates.' It does not explicitly name alternatives or say when not to use it, but the domain boundary is clear enough against the sibling tools.

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