browser_watch

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that this is a live capture, that coordinates are window pixels rather than page coordinates, and that it is unsuitable for action. However, it doesn't explicitly state the return format (e.g., single frame vs. continuous stream) or how/when the capture stops, which is a modest gap.

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 appropriately short and front-loaded: the first sentence defines the tool's core behavior, the second provides usage constraints and an alternative. Every sentence serves a purpose with no redundant filler.

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 zero-parameter watch tool, the description is largely complete, covering purpose, limitations, and a recommended sibling alternative. The main omission is the exact delivery/return mechanics of the 'live capture' and whether any session or lifecycle management is required, especially since no output schema exists to fill that gap.

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 tool has zero parameters and the schema is empty, so no parameter description is needed. The description still enriches the tool's semantics by describing what is captured (tab strip, address bar, page, pointer), matching the baseline expectation for a parameterless tool.

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 clearly states what the tool does: it shows the whole browser window (tab strip, address bar, page, pointer) via a live capture on the active tab. It also explicitly frames the tool as 'watching the work, not for acting on it,' which differentiates it from siblings like browser_click_at and browser_take_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?

The description gives direct usage guidance: use it for watching, not for acting, and explicitly warns against feeding its coordinates to browser_click_at, directing the agent to browser_take_screenshot instead. This makes the choice between sibling tools clear.

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