see-frame

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

No annotations exist, so the description carries the burden. It transparently discloses downscaling (maxWidth 512), native-resolution option (maxWidth 0), performance/cost rationale, and the still-vs-playback caveat. This provides valuable behavioral context beyond the schema.

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 moderately long but every sentence earns its place: use case, selection method, output caveats, and defaults. It front-loads the core purpose with 'SEE what a composition actually looks like' and remains readable despite the detail.

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?

With no output schema and no annotations, the description adequately explains return type (images), parameter defaults, and behavioral caveats. It leaves some details to the schema (e.g., timeoutMs) but covers the core usage envelope well, including the self-correct workflow.

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%, so baseline is 3. The description adds meaning around maxWidth (fast/cheap, native resolution), comp selection (name/index/active), and underscores the still limitation. This enriches, rather than merely repeats, schema descriptions.

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 it renders composition frames to images for visual verification, using specific verbs like 'render' and listing concrete problem cases (clipped text, wrong colors, RTL shaping). This distinguishes it from siblings like inspect-comp (structured state) and other render tools.

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 says to use 'after edits' to catch visual issues, and gives examples of problems the DOM doesn't reveal. It also implies when_not_to_use by noting time-based effects differ from playback, but doesn't name alternative tools directly (though includeState references inspect-comp).

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