run_action

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

With no annotations provided, the description carries the full burden, but it does disclose key behavioral traits: it returns status per step, handoff on stop, and tokens reported by API. It also mentions the timeout behavior, which is significant. However, it does not elaborate on error handling, side effects, or what happens to browser state after the call. The description partially covers the safety/side-effect profile, but lacks depth on failure modes and browser state changes.

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 reasonably concise, with three sentences covering the main functionality, return values, and a pointer to more detailed instructions. It front-loads the purpose and then covers the grouping and return information. There is some redundancy with the schema, but the description is efficient and not bloated.

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 (14 parameters, nested objects, no output schema), the description is insufficiently complete. It mentions return values (status, handoff, tokens) but does not detail the exact structure of those returns, which is critical for an agent to parse the results. It also relies on 'Read this server's instructions' for step shapes, which is an external reference and may not be available to the agent. The description needs more detail on return format and step syntax to be 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?

Schema description coverage is 100%, so the schema already documents every parameter in detail. The description adds minimal extra meaning beyond what the schema provides, such as the concept of 'independent errands' and 'one tab each'. It does not add syntax or format details beyond the schema definitions. Baseline 3 is appropriate given high coverage.

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 that the tool drives a browser through user-written steps with Jev choosing actions, and covers multiple independent errands via groups and tabs. It distinguishes from the sibling 'use_jev_raw' by emphasizing the step-driven and group orchestration, though it does not explicitly name the sibling.

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 provides strong usage guidance: it recommends using groups for independent errands to avoid multiple calls, and mentions that steps should be single actions. It implicitly sets expectations for when to use the tool, but doesn't explicitly contrast with 'use_jev_raw' or state when not to use it. The guidance is clear for typical browser automation scenarios.

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