computer.execution

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

With no annotations, the description must carry the full burden of behavioral disclosure. It only reveals that the tool does not affect the user's foreground desktop, but it fails to disclose that 'destroy' is destructive, what 'diagnose' entails, or any side effects of actions. The isolation trait is useful but insufficient for a tool with create/destroy operations.

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 a single, front-loaded sentence with no wasted words. It clearly states the core purpose and key benefit in a compact form. However, it is slightly under-specified for the number of actions, but the structure itself is efficient.

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 the tool has five distinct actions including a destructive 'destroy', no output schema, and no annotations, a one-line description is far from complete. It leaves unclear what each action does, return values, and operation-specific contexts. The presence of many sibling tools increases the need for further clarification.

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?

The input schema already covers parameter semantics well: 'action' has an enum of five values, and 'commandLine' is described as only required for 'launch'. The description adds no extra meaning to the parameters, so it stays at the baseline level of relying on 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 identifies a specific resource (Windows dedicated execution desktop) and a verb (manage), also noting a key differentiator (does not affect the foreground desktop). While it is not exhaustive about operations, the schema clarifies the action list, and the description distinguishes from siblings like computer.invoke or shortcut.run by focusing on an isolated desktop.

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?

No guidance is given on when to use this tool versus alternatives such as computer.invoke, shortcut.run, or computer.act. The description simply states what it does without prerequisites, exclutions, or hints about the intended use case.

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