Act in browser

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

Annotations already disclose destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds 'revision-aware,' which hints at concurrency control via expectedRevision, but doesn't explain the mechanism or consequences. It provides some extra context beyond annotations but remains vague about side effects and failure behavior.

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 sentence with no filler. Key elements—scope ('one'), routing modes, and revision awareness—are packed in. It is economical and front-loaded, though the jargon ('revision-aware', 'human browser action') may reduce clarity slightly. It earns its place but could be more accessible.

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 complexity (8 parameters, nested target object, no output schema) and low schema coverage, the description is far from complete. It doesn't mention that action must come from browser_capabilities, how to specify the target, retry semantics, or the expectedRevision contract. An agent would struggle to invoke this tool correctly based on the description alone.

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 low (25%), so the description must compensate for undocumented parameters like params, target, retries, timeoutMs, retryDelayMs, and expectedRevision. It does not describe any of these; the only implicit hint is 'DOM, browser-input, or native routing' for the engine parameter. This fails to help the agent understand how to construct valid invocations.

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') and resource ('human browser action'), and the word 'one' distinguishes it from browser_batch. It also mentions routing through DOM, browser-input, or native, which clarifies its scope. However, it doesn't explicitly name siblings or state that action names come from browser_capabilities, so it's clear but not maximally differentiating.

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?

There is no guidance on when to use this tool versus alternatives (e.g., browser_batch for multiple actions, browser_query for reading state). It doesn't mention prerequisites like calling browser_capabilities first or supplying expectedRevision. The description simply states what it does, leaving the agent to infer usage context entirely.

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