computer.invoke

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

With no annotations provided, the description carries the transparency burden. It adds a meaningful behavioral detail: 'high-risk operations return a one-time confirmation token' and notes that actions are 'restricted'. However, it does not clarify side effects, permissions, reversibility, or how the token should be used, leaving significant gaps for a tool that executes actions.

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 filler. It immediately establishes the preferred-entry role and the core behavior. It is concise but perhaps too sparse given the tool's complexity, so it earns a 4 rather than a 5.

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?

This is a complex tool with 5 unannotated parameters, nested objects, no output schema, and several sibling execution tools. The description only covers high-level purpose and one safety behavior. It omits the format of actions, the meaning of window/params, return behavior, risk conditions, and how it relates to shortcut.run, computer.act, or computer.execution.

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 must compensate. It indirectly maps 'saved shortcut' to shortcut_id, 'restricted actions' to actions, and 'confirmation token' to confirm_token, but it does not explain the 'window' or 'params' fields, nor the structure of action objects. This partial compensation is insufficient for 5 unannotated parameters.

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's function: 'execute a saved shortcut or a set of restricted actions' and frames it as the 'preferred entry' point. It names a specific verb and resource, but it does not explicitly differentiate it from sibling tools like shortcut.run or computer.act, so it falls short of a 5.

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 phrase 'preferred entry' implies this tool should be used first, and 'restricted actions' hints at a limited scope, but it provides no explicit alternatives, exclusions, or conditions for when to choose another sibling tool. This is implied usage guidance rather than explicit guidance.

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