interact

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns 'the emitted intent messages and the access tree afterwards' and that a screenshot can be requested. It also clarifies the interaction method (semantic selectors, not coordinates). However, it does not mention side effects, permissions, or whether interactions are synchronous, which would improve transparency.

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 with no redundant information. It front-loads the core action ('Drive a UI through scripted interactions'), then specifies supported actions, constraints, and return values. Every sentence is necessary and contributes to understanding.

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 (5 parameters, no output schema, no annotations), the description provides essential information about purpose and returns but misses contextual details like error handling, sequencing (e.g., need to render UI first), or any limitations. It is adequate for a simple use case but lacks completeness for robust agent decision-making.

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 60%. The description adds value for the 'steps' parameter by providing an example format, and for 'screenshot' by explaining its effect. However, parameters like 'size', 'theme', and 'description' are not elaborated beyond the schema, leaving the agent to rely on their names. The description partially compensates for gaps but does not fully cover all 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 purpose: 'Drive a UI through scripted interactions' and lists supported actions (click, type, key, tab, hover, wheel, drag) with the constraint 'by semantic selector, never coordinates'. This distinguishes it from sibling tools like render_ui (which renders) and query_ui (which queries). The verb 'Drive' with 'scripted interactions' is specific and unambiguous.

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 implicitly guides usage by specifying 'by semantic selector, never coordinates', but it does not explicitly state when to use this tool versus alternatives like run_scenario or describe_schema. No exclusion criteria or prerequisites (e.g., needing a rendered UI) are mentioned, leaving the agent to infer context.

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