see-frame

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

Despite no annotations, description thoroughly explains behavior: returns downscaled images by default, maxWidth 0 for native resolution, clamping of out-of-range times, still vs playback differences, motion blur param default false, and time-dependent effects caveat. Covers all key behaviors.

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?

Compact yet comprehensive. Front-loaded with purpose and use cases. Every sentence adds value without redundancy. Well-organized flow from purpose to parameter specifics to caveats.

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 6-parameter tool with no output schema, description covers all parameters, return format, default behaviors, caveats (still vs playback), and selection mechanisms. No gaps for agent to interpret.

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%, but description adds significant meaning: comp selection via name/index/active, time defaults to midpoint, maxWidth default 512, motionBlur default false, includeState for structured state. Explains rationale behind parameters and their effects.

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 the tool renders frames to images for visual verification, listing specific problems like clipped text or wrong colors. It distinguishes from siblings by mentioning 'inspect-comp' for structured state, which is also available via includeState.

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?

Explicitly states when to use: after edits to catch visual problems not revealed by DOM. Lists specific scenarios (clipped text, blown-out glow, etc.). Does not explicitly state when not to use, but provides clear context and mentions optional includeState for structured info.

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