computer_workflow

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

The annotations already flag the tool as non-read-only and destructive, and the description adds substantial behavioral context: the engine switches apps and stages without returning control, holds desktop ownership until completion, and leaves native apps open. It also names explicit follow-up mechanisms, making the blocking/lifecycle behavior clear.

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 seven short sentences, each earning its place: purpose, orchestration behavior, input requirements, inputsFrom semantics, desktop ownership, and monitoring/cancellation. It is front-loaded with the core purpose and contains no filler or repetition.

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 complex workflow tool with no output schema, the description covers what the tool does, how to structure stages, desktop ownership, and how to monitor or cancel. It does not explain return values or the behavior of optional parameters like timeoutMs and minConfidence, but those are partially encoded in defaults and schema, making the description adequate but not fully complete.

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?

With 0% schema description coverage, the description must compensate, and it does add useful meaning for stages (goals, exact inputs, observable conditions) and precisely explains inputsFrom as copying one observed field from an earlier zero-indexed stage. However, it does not explain the other top-level parameters (ocr, timeoutMs, minConfidence) or the until-condition variants, leaving optional tuning behavior undocumented.

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 clearly states the tool starts an ordered macOS workflow in one call and distinguishes it from step-by-step interaction by noting it switches apps and runs stages without returning to the assistant. It does not explicitly name sibling tools, and the term 'Jev stages' is unexplained jargon, which slightly reduces clarity.

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 implies use for multi-stage macOS workflows and provides lifecycle guidance by telling the agent to poll computer_status or stop with computer_cancel. However, it never explicitly contrasts this tool with siblings such as computer_act, computer_run, or computer_execute, nor does it state when not to use a workflow.

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