Browser (debug): act

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

Annotations already declare destructive=true and readOnly=false, but the description adds concrete context they don't carry: injected scripts persist until explicitly removed, and login consumes a real vaulted credential that is never returned. It also flags the whole tool as state-changing/high-risk and notes that the result is a dispatch result requiring re-snapshot to confirm. Missing only deeper detail like failure modes or per-action side effects.

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?

Front-loaded with the action list, then the risk disclosure, then the sibling routing and return/verify note; every sentence carries information. The action enumeration slightly duplicates the schema enum, but it functions as a useful triage summary rather than padding.

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?

With no output schema, the description usefully states what comes back ('the dispatch result') and how to confirm it ('re-snapshot to verify'). Combined with the risk disclosures for inject/login, an agent has enough to call it correctly, though per-action failure behavior and the destructive implications of stop/force_restart are left to the schema.

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 embeds the required-parameter mapping and per-action semantics, so the schema does the heavy lifting. The description only restates the action groupings at a high level, adding no syntax or format detail beyond what structured data provides. Baseline 3 is appropriate.

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?

States a specific verb (act) and resource (NAVIG-launched debug browser), then enumerates the action families so an agent knows the full surface covered. It explicitly distinguishes itself from the sibling navig_browser_debug, which is the inspection/refs tool, so the two can be told apart without opening schemas.

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?

Offers a clear routing rule: 'Use navig_browser_debug to inspect and get refs first,' plus a post-action rule to 're-snapshot to verify.' That is real when-to-use guidance with a named alternative. It does not, however, contrast against the other browser sibling (navig_browser_user) or say when NOT to use this high-risk path.

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