compare_screenshots

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

With no annotations provided, the description carries the full burden of disclosure. It discloses the comparison method (pixel by pixel) and the output shape (change count + diff image), but it omits important behavioral details such as how the threshold parameter affects the comparison, what happens with invalid/mismatched images, or whether the diff image is returned as a path or base64.

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 a single, well-structured sentence that front-loads the core action and quickly lists input formats and outputs. Every phrase adds value, and there is no redundant 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?

The description covers the main purpose, input types, and output summary, but it lacks critical context like threshold semantics and any error/edge-case behavior. Since there is no output schema, the description should more precisely define what 'change count' and 'red-highlighted diff image' mean in practice, but it does provide a reasonable high-level summary.

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 input schema provides only basic types and a default for threshold, with no parameter descriptions. The description adds meaningful semantics for image_a and image_b (res:// or user:// paths, or raw base64), but it entirely omits threshold, leaving its purpose and behavior undocumented.

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 clearly states a specific verb (compare), a specific resource (two PNG images), and the expected outputs (change count and red-highlighted diff image). It is distinct from sibling tools that capture or generate screenshots, and it has no ambiguity about what the tool does.

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 the tool is used for comparing PNG screenshots, but it provides no explicit guidance on when to choose this tool over alternatives (e.g., get_editor_screenshot, get_game_screenshot, or capture_frames). There are no usage contexts, exclusions, or prerequisites stated.

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