browser_watch

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

Annotations already mark the tool as read-only and non-destructive, and the description adds substantial runtime detail: it is a live capture kept running, called many times a second, outputs window pixels rather than page coordinates, and returns an idle response when no browser window exists. This goes well beyond the annotation flags and does not contradict them.

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 compact and front-loaded: purpose first, usage warning second, idle behavior third. However, phrases like 'answers the sentence that says so' and 'live panes' are opaque and make the final sentence harder to parse than necessary.

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?

The description covers the view contents, the coordinate warning, the no-start behavior, and the closed-browser case, which is strong for a one-parameter tool. With no output schema, though, it leaves the result format somewhat ambiguous, mixing the idea of a live visual capture with the notion of answering with a sentence.

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?

The only parameter, browser, is already fully described in the input schema, including the default of main and the meaning of support, and schema description coverage is 100%. The description adds no parameter-specific meaning, so the schema carries the semantic burden.

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 defines the tool as showing the whole browser window as a person sees it, including tab strip, address bar, page, and pointer, from a live capture. It explicitly separates watching from acting and distinguishes itself from browser_take_screenshot and browser_click_at, so an agent can tell it apart from its siblings.

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 states directly 'For watching the work, not for acting on it' and gives an explicit exclusion: do not feed its coordinates to browser_click_at; use browser_take_screenshot for that. It also says 'Starts nothing,' clarifying that this tool is not a substitute for opening a browser.

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