computer_run

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

Annotations already declare readOnlyHint=false and destructiveHint=true. The description adds useful behavioral context: 'Jev chooses actions; code independently verifies completion' and 'This tool operates the target app; only request actions the user authorized.' This adds some value, though the destructive nature implied by annotations is not explicitly reinforced.

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 compact and front-loaded: it states the core action first, then requirements, behavior, and safety in four sentences. No sentence is wasted and the most decision-relevant information appears early.

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 high complexity (7 params, nested until objects, no output schema), the description covers the essential purpose and key constraints but omits how maxSteps, timeoutMs, and minConfidence affect behavior. It also does not mention how to use the returned ID with sibling tools like computer_status or computer_continue, which would help an agent after calling this tool.

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%, so the description carries the burden of explaining parameters. It meaningfully clarifies the 'until' parameter ('at least one observable until condition', 'All until conditions must pass') and hints at the 'inputs' parameter ('Supply exact text in inputs'). However, sessionId, maxSteps, timeoutMs, and minConfidence receive no semantic explanation, leaving gaps.

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 states a specific verb and resource: 'Start a bounded Jev automation task and immediately return its ID.' This clearly conveys what computer_run does. However, it does not explicitly differentiate from siblings like computer_act or computer_execute, so it stops short of full sibling distinction.

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 requirements: supply exact input text, provide at least one observable until condition, and ensure all conditions pass. It also indicates this is for bounded automation tasks. It provides good context but does not explicitly state when to choose this over alternatives or when not to use it.

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