capture_adb_screen

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

Beyond annotations, it adds useful mechanics: the capture uses `screencap -p` through exec-out, creates no device-side file, writes into an output directory, and reports a digest and dimensions. It remains consistent with readOnlyHint=false because it creates a local PNG, and it does not overstate destructive behavior.

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 two compact sentences, front-loads the core action, and includes only relevant technical detail. Every clause contributes to understanding what the tool does or does not do.

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 three-parameter tool with full schema coverage and no output schema, the description is largely sufficient: it explains the capture mechanism, output location, digest, dimensions, and exclusions. It could be slightly more complete about the digest format or failure behavior when the target file already exists, but the schema covers the latter.

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 100%, so all three parameters are already documented. The description adds only the notion of a caller-selected output directory and does not explain serial selection or analysis_project_id beyond what the schema 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 states a specific verb and resource: capture one frame of the device screen as a PNG. It also scopes the operation by noting it is not recording or interaction, which distinguishes it from nearby UI/runtime siblings.

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 clearly establishes the intended use case: a single-frame screenshot into a caller-selected directory. It also gives an exclusion, 'No recording or interaction,' but does not explicitly name when to prefer sibling tools such as capture_ui or inspect_adb_display.

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