Take screenshot

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

Annotations already establish that this is a safe, read-only, non-destructive, idempotent operation. The description adds useful behavioral context by stating that output is written under `.swebsy-agent/screenshots/`, that the file path is returned, and that whole-page screenshots downscale section detail.

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 three tight sentences. The primary action is front-loaded, the return value is stated, and the `targetPath` guidance explains its purpose without unnecessary repetition.

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?

There is no output schema, so the description correctly states that the file path is returned. All three parameters are documented in the schema, and the annotations cover safety. An agent has enough information to select and invoke the tool correctly.

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 coverage is 100%, so the baseline is 3. The description exceeds that by explicitly explaining when to use `targetPath` and why it matters; however, it does not add practical meaning for `selectionOnly` or discuss viewport tradeoffs beyond what the schema already provides.

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 and resource: 'Capture a styled screenshot of the current page at a fixed viewport.' It also states where the file is written and what is returned, so an agent can distinguish this from page-reading or export siblings without opening the 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?

It gives explicit guidance for using `targetPath` when verifying one section, and explains why a whole-page capture is unsuitable for component detail. It does not explicitly cover when not to use the tool or name alternatives, but the context is clear enough for correct invocation.

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