browser_act

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

With no annotations, the description carries the full burden and does disclose meaningful traits: it performs 'real input' (real side effects), waits for the page to settle before returning, returns a diff of what changed rather than full state, and can surface approval.required/handoff.required outcomes. It does not mention reversibility, permissions, or that actions like upload/click are irreversible, which keeps it short of a 5.

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 dense and front-loaded: the core behavior (act, wait, return diff) comes first, followed by the action list and then the special submit/handoff rules. The action enumeration is long but each entry earns its place by disambiguating parameter usage. Slightly telegraphic phrasing costs it the top score.

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?

For a complex 10-parameter mutation tool with no annotations and no output schema, the description covers the essentials: what it does, which params pair with which actions, and how to handle approval/handoff replies. Gaps remain around approvalId, the provenance of ref values, and the shape of the diff returned, but nothing critical to invoking it correctly is missing.

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 only 20% and there are 10 parameters, so the description must compensate — and it largely does. It maps parameters to actions: text for fill/type, key for press, value/values for select (values for multiple lists), to for scroll (top|bottom or a ref location), paths for upload, and submit:true to make fill press Enter. It omits approvalId's purpose and doesn't explain where valid refs come from.

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+resource: acting on an element identified by ref using real input, then waiting for the page to settle and returning only what changed. It enumerates every supported action (click, fill, press, check, uncheck, select, hover, scroll, type, upload), which immediately separates it from read-only siblings like browser_read and browser_screenshot.

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?

Usage is implied rather than stated: the agent must infer that this is the write/interaction tool used after browser_open/browser_read, and no comparison to browser_batch or browser_call is given. It does provide one concrete routing rule — if the reply is approval.required or handoff.required, call browser_wait_human — which is genuinely useful but narrow. There are no explicit when-not-to-use conditions.

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