browser_watch

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

No annotations are provided, so the description carries the full behavioral burden, and it does substantial work: it starts nothing, refuses rather than opening a browser to photograph, and discloses that main and support share nothing. It stops short of describing the return payload (image format/size) or any rate or cost implications of a high-frequency capture.

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-loads what the tool shows, then the usage boundary, then the precondition. Prose is slightly literary ('a look is not a command') but every sentence carries distinct information and nothing is redundant.

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 one-parameter, no-output-schema read tool, it covers purpose, alternative, precondition, and parameter default/isolations. The main omission is what the returned capture looks like (image bytes vs encoded frame), which an agent might want before invoking repeatedly.

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 0% and the schema only carries the enum values, so the description must compensate. It does: it explains that `browser` defaults to `main` unless `support` is specified, and adds that the two are fully isolated, which is meaningful for a single optional parameter.

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 resource and modality: the whole browser window as a person sees it, including tab strip, address bar, page and pointer, from a live capture. It explicitly distinguishes itself from browser_take_screenshot and browser_click_at, so an agent can tell what this returns without opening a 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?

Gives explicit when-to-use ('for watching the work'), when-not ('not for acting on it', 'do not feed its coordinates to browser_click_at'), and names the alternative (browser_take_screenshot). It also states the precondition behavior (refuses if no browser is running) and notes the live panes call it many times a second.

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