computer_close

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

The description meaningfully extends the destructiveHint annotation by specifying exactly what is affected: the automation browser or native session, while native applications remain open. It also discloses a required precondition: cancel and wait for running tasks first. This gives the agent concrete knowledge about side effects and sequencing beyond the annotation alone.

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 short sentences deliver all key information without filler. The primary action is front-loaded, and the caveat and precondition follow naturally. Every sentence adds value.

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 single-parameter destructive close operation, the description covers the main behavioral details and the critical precondition. It does not explain sessionId provenance or return values, but there is no output schema and the operation is straightforward. Sibling tools like computer_sessions can reasonably supply the missing session ID context.

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 0%, and the description never mentions the sessionId parameter or where it comes from. The parameter name is self-explanatory to a degree, but the description does not explain how to obtain it, what format it should take, or whether it refers to an automation session vs. a native session. Given low schema coverage, the description should have compensated for this gap.

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 uses a specific verb ('Close') and names two concrete targets: an idle automation browser or a native session. It also clarifies that native applications remain open, which helps distinguish this from a broad 'kill everything' operation. It does not explicitly name sibling tools, but the behavior is clear enough.

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 usage context: the tool is for idle automation browsers or native sessions, not for active native applications. The instruction to 'Cancel and wait for any running task first' provides explicit ordering guidance and implies this tool should not be used while tasks are still running. It does not explicitly mention alternatives like computer_cancel or computer_sessions, but the intended usage is largely inferable.

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