watch

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals key behaviors: polling until change, returning the changed screenshot, requiring explicit window/process identification, and the screen mode sentinel. It does not describe side effects (though a watch operation is inherently non-mutating) or error behaviors, but the explicit constraints and workflow are well covered.

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 extremely concise—only two sentences—yet packs in the primary action, the return value, and critical constraints. It is front-loaded with the verb and resource, making it easy to scan. No unnecessary words.

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?

Given the tool's moderate complexity (five parameters, no output schema, no annotations), the description covers the essential context: what it does, the requirement for window_title/process_name, and the screen mode sentinel. It does not explain timeout behavior or return format in detail, but these are partially covered by the schema's parameter descriptions. A complete description could mention the timeout fallback, but this is still fairly complete.

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 input schema already provides 100% coverage with detailed descriptions for all parameters, including the requirement for either window_title or process_name and the mode options. The description reinforces these constraints (e.g., frontmost not supported, '__screen__' sentinel) but adds minimal new meaning beyond what the schema already offers. The high schema coverage warrants a baseline 3.

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 the tool's purpose: to poll a window until its visual content changes, then return the changed screenshot. It uses a specific verb ('poll') and resource (window content), which distinguishes it from siblings like 'capture' or 'see' that likely take single snapshots.

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 provides clear context on when to use the tool: when you need to watch for visual changes in a window. It also includes important exclusions (frontmost capture not supported) and a specific requirement (window_title or process_name). However, it does not explicitly compare to alternatives or state when not to use it beyond the frontmost limitation.

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