browser_act

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

With no annotations, the description carries the full burden. It usefully discloses post-conditions (returns a fresh snapshot) and orchestration behavior (rechecks targets, applies domain and irreversible-action gates), which hints at the allow_irreversible parameter's role. It stops short of explaining what the gates actually block, whether mutations are reversible, or failure/partial-batch semantics for the ops array.

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 tight sentences with no filler, and the core purpose is front-loaded before the snapshot and gating details. Efficient, though the gating sentence is somewhat jargon-dense for the space it consumes.

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?

An output schema exists, so return-value explanation is not required, yet the description adds a useful note about the fresh snapshot. For a multi-op mutation tool with no annotations and only 33% schema coverage, the description leaves meaningful gaps around the irreversible gate semantics and operation-specific requirements.

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 (33%) and the description adds nothing about the three top-level parameters or the meaning of the nested ops fields. Critically, the 14-value action enum and per-action required fields (ref, name, text, value_key, etc.) are not clarified, even though the schema descriptions only partially cover them. The description does not compensate for the coverage gap.

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 (perform) and resource (manual browser operations) scoped to 'current element refs in an existing session', which distinguishes it from browser_run (new session) and browser_observe (observation only). It does not enumerate the operation set from the action enum, so the exact scope remains slightly abstract, but an agent can still tell what class of tool this is.

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 phrase 'in an existing session' implies it should be used after browser_run, and 'a separate browser_observe is not needed after it' clarifies its relationship to that sibling. However, there is no explicit when-to-use guidance versus browser_navigate, browser_tabs, or browser_observe beyond that single aside, and no stated prerequisites for the session.

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