computer_act

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

The annotations already declare destructiveHint=true and openWorldHint=true, so the description does not need to repeat that. The description adds valuable behavioral constraints beyond annotations: 'No selectors or executable code' clarifies what this tool cannot do, and 'against a fresh observation' indicates that it operates on the latest observation. These details help the agent avoid misuse without contradicting any annotation.

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 two sentences long and front-loaded with the core action ('Execute one precise action'), followed by a key constraint ('No selectors or executable code') and a routing hint ('For several steps prefer computer_run'). Every sentence earns its place with no fluff 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?

Given the tool's complexity (multiple action kinds) and the rich schema that documents them, the description covers the essential context: single action, fresh observation, returned state, and the alternative for multi-step workflows. It does not describe the output format, but no output schema exists and the description says it returns 'the resulting state', which suffices. The destructive nature is covered by annotations. Minor missing details (e.g., that the action must target an element from the observation) are implied by the schema and the 'fresh observation' phrasing.

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 by explaining the parameters (sessionId, observationId, action). It does not. While the schema itself is detailed (listing action kinds like click, fill, scroll), the description adds no semantic meaning to the parameters. 'Against a fresh observation' hints at observationId but does not explain sessionId or the structure of the action parameter. This is a significant gap for a tool with three required 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 states a specific verb ('Execute'), a precise resource ('one precise action against a fresh observation'), and the result ('return the resulting state'). It explicitly differentiates from the sibling computer_run by saying 'For several steps prefer computer_run', making the purpose unambiguous and distinguishing it from alternatives.

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 explicit usage guidance: it names the alternative computer_run and the condition under which to prefer it ('For several steps'). It also implies that this tool is for a single action against a fresh observation, which clarifies when it should be chosen over other siblings like computer_inspect or computer_execute.

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