Compare screenshots

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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description adds the crucial context of why it is a write operation — it can save a difference image to disk. However, it does not warn that writing to diffSavePath may overwrite an existing file, nor does it describe what the returned metrics contain or how threshold affects them.

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 front-loaded sentence with no filler. It is arguably too terse for a 6-parameter tool, but every word earns its place and the core action leads.

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 6 parameters, no output schema and no schema descriptions, the description should at minimum explain the compared inputs, the threshold semantics and the diff-image output. None of this is present, so an agent cannot call it confidently beyond the two required paths.

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 0% across 6 parameters, so the description carries the full burden and fails to compensate. Only diffSavePath is obliquely referenced ('save a ... difference image'); threshold, beforePath, afterPath, deviceId and deviceName are never explained, and the threshold's 0-255 default of 24 is left opaque.

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 gives a specific verb+resource ('compute pixel-level visual change metrics') plus an optional side effect ('save a red-channel difference image'), which is enough to distinguish it from screenshot_capture, adb_screenshot and other capture siblings. It never explicitly says the metrics are computed between the two screenshot paths, but the before/after pairing is strongly implied.

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 when-to-use guidance, no mention of prerequisites (both required paths must exist), and no hint about when the optional diff image is worth producing versus just reading metrics. The agent gets no routing help against the many screenshot-related siblings.

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