Screenshot

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

The annotations already declare readOnlyHint:true, so the safety profile is covered. The description adds the dependency on the Google android CLI for annotate mode and clarifies that the result is returned as an image. It also adds context about the annotate feature's coverage (text in images/WebViews), which is beyond the schema description. No contradictions with annotations.

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 sentences, both earning their place. The first sentence states the core function; the second explains the optional annotate behavior and notes the sibling comparison. No redundant wording or fluff.

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 screenshot tool with readOnlyHint and no output schema, the description covers the primary action, return format, optional parameter behavior, a prerequisite, and a sibling differentiation. Given the tool's simplicity and the sibling context, this is sufficiently 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?

Schema coverage is 100% with descriptions for both serial and annotate. The description adds meaning to annotate by explaining the numbered bounding boxes and the limitation that the Google android CLI is required. It also highlights the advantage over snapshot_ui, which enriches parameter understanding 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?

The description uses a specific verb ('Take') and resource ('device/emulator screen'), and states the output ('return it as an image'). It clearly differentiates from siblings by mentioning the annotate feature's ability to see text inside images/WebViews that snapshot_ui cannot.

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 comparative guidance by noting that annotate:true can see text inside images/WebViews that snapshot_ui cannot, implying when this tool is preferable. It also mentions the prerequisite of the Google android CLI for annotate. However, it does not explicitly state when to avoid this tool or how it compares to other alternatives like snapshot_ui beyond this one capability.

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