screenshot

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

With no annotations provided, the description carries the full burden. It discloses the output format (PNG) and the effect of the `id` parameter, but does not mention side effects, required app state, error behavior, or whether the screenshot is returned inline, saved, or accessible via a path.

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?

A single, front-loaded sentence that conveys both the main operation and the optional mode with zero wasted words. The conditional clause about `id` is placed efficiently and reads clearly.

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 simple capture tool, the description covers the essential behavior and the optional element targeting. However, with no output schema and no annotations, it could usefully mention what the returned PNG is (path, data, etc.) and how `app_id` relates to the running app.

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%, so the description must compensate. It explains the meaning of `id` (selects an element) but gives no meaning for the required `app_id`, leaving a key parameter undocumented.

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 uses a specific verb ('Take') and resource ('PNG screenshot'), and clearly distinguishes between whole-page and element-level capture via the `id` parameter. This separates it from sibling tools like `click` or `list_controls`.

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 implies usage: call it when you need a visual snapshot of the page or a specific element. However, it does not explicitly state when to prefer this over alternatives such as `read_outputs` or `show`, nor does it mention any prerequisites like an active app.

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