take_screenshot

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

No annotations are provided, so the description must carry the behavioral disclosure burden. 'Take a picture' does imply a non-destructive capture and distinguishes it from get_screen's accessibility-tree output, but it does not state the return format, potential capture limitations, or device requirements. It is minimally adequate but not transparent about edge behaviors.

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 short sentences with no filler. The primary action is front-loaded, and the conditional use case follows immediately. Every word contributes to selection or invocation.

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 tool with no output schema, no annotations, and no parameter descriptions, the description is too thin to fully prepare an agent. It explains when to use it but not the meaning of its two parameters or what the return value looks like. The core purpose is clear, but operational details are missing.

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 schema has 0% description coverage and the description never mentions 'device' or 'max_width.' An agent cannot determine what the parameters mean, what formats are accepted, or how max_width affects the result. The description adds no semantic value beyond the raw parameter names.

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 states a specific verb and resource ('Take a picture of the phone screen') and explicitly distinguishes itself from get_screen by naming when that sibling is insufficient. The examples (videos, games, photos, custom-drawn interfaces) make the tool's purpose concrete.

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 a clear conditional for when to use this tool: 'Use this when get_screen doesn't show what you need.' It also names the alternative tool and the scenarios that favor this one, giving an agent actionable routing guidance.

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