adb_screenrecord

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does reveal the full pipeline (record → pull → path) and implies the output is a local file path rather than raw bytes. However, it doesn't disclose the default file location, that the file persists on disk, or that a device-side temp file is created/managed.

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?

A single concise sentence that front-loads the core action and states the full workflow compactly. No filler words. Could arguably add one more sentence about defaults without bloating it.

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?

The tool has 3 params with no output schema and no annotations, so the description is the sole source of behavioral info. It covers the main flow adequately, but given the absence of annotations and output schema, it would benefit from disclosing defaults (10s, /tmp path), max duration limit (180s), and that the return value is a file path.

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 only 33% (only 'serial' has a schema-level description). The description mentions N seconds and a local mp4, mapping loosely to 'seconds' and 'local_path', but doesn't define whether local_path is an absolute/relative path, file format requirements, or destination directory existence. It adds some value beyond the sparse schema but doesn't fully compensate for the coverage gap.

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 clear verb ('Record') with a specific resource ('screen') and describes the full workflow (record, pull to local mp4, return path). This distinguishes it from siblings like adb_screenshot (static capture) and adb_logcat (stream logging), though it doesn't explicitly name an alternative.

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 implies usage for capturing video over a duration, which contrasts with adb_screenshot for stills, but it doesn't explicitly state when to choose this vs alternatives. No exclusions or prerequisites (e.g., device must support screen recording) are given.

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