Browser (user): inspect and act

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

Annotations declare destructive/openWorld/non-idempotent, and the description adds genuine context beyond them: the first console/network call starts capture, screenshots write a file to disk, and act runs under a visible overlay. The schema further discloses that dialog handling, password/card typing and uploads require user confirmation. It stops short of describing rate limits, session lifetime, or failure modes.

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?

Three sentences, front-loaded with the capability list, then routing guidance, then the return shape. Every clause carries information; it is dense but not padded, and sized appropriately for a ten-action tool.

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?

No output schema exists, so the description must cover returns, and it does at a useful level ('tab ids, page text/tree, capture entries, or per-step results'). Combined with a fully documented schema for a 21-parameter multi-action tool, the main residual gap is lifetime/session-management guidance around release.

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% and the action enum carries exhaustive per-action required-parameter and behavioral documentation, so the schema does the heavy lifting for all 21 parameters. The description only paraphrases the action families it already lists; baseline 3 is correct when structured fields are this complete.

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 names a specific verb set and resource ('the operator's own browser through Dock') and enumerates the capability families (tabs, snapshot/text, console/network, screenshot, act). It explicitly distinguishes itself from the sibling navig_browser_debug and states it never silently falls back to it, so an agent can route without opening either schema.

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?

It names the alternative tool explicitly ('Use navig_browser_debug for a NAVIG-launched debug browser') with the condition that selects it, and reinforces the exclusion with 'this never silently falls back to one'. It does not, however, mention navig_browser_debug_act or any guidance on choosing among the ten internal actions from the description itself.

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