screenshot

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

No annotations are provided, so the description carries the full behavioral burden. It discloses only the PNG format; it does not say whether the image is returned inline, written to a path, or how large/complex screens are handled, nor whether any permissions or a connected device are required.

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?

Two words plus a parenthetical — front-loaded and free of padding. It is arguably under-specified rather than bloated, but as pure conciseness it is efficient.

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, likely read-only capture tool with one optional well-documented parameter, the description is minimally adequate. The PNG hint is useful, but with no output schema the description should clarify the return shape (inline image vs. file path), which it omits.

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 single optional 'serial' parameter is fully documented in the schema (100% coverage, including the default-resolution behavior), so the baseline of 3 applies. The description adds nothing about parameter meaning beyond the schema.

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?

States a specific verb+resource combination ('Take a screenshot') and adds the output format (PNG). No sibling tool covers screenshots, so no explicit differentiation is needed, but the description never mentions the device-targeting dimension the sibling set (serial-based ADB tools) implies.

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?

There is no guidance on when to use this tool, no prerequisites (e.g., an active device connection), and no mention of alternatives such as ui_dump for structured UI inspection. The agent must infer usage entirely.

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