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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. Beyond that the description discloses the return form ('you get the still back as an image') and that output is sized to the named format so the preview matches the real aspect ratio — useful behavior not encoded elsewhere, though it does not discuss cost or latency of a render.

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?

Front-loaded with the core action, then the usage loop, then the alternative. Four sentences, each carrying distinct information (what, when, what you see, when to use something else) with no repetition of the schema.

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?

No output schema exists, and the description covers the return value (a still image), the failure modes it is meant to catch, and the relationship to composition clips. For a 4-parameter read-only preview tool, nothing needed to invoke it correctly is missing.

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 the baseline is 3. The description adds real meaning on top: it tells the agent to pass the SAME html and tokens as a {kind:"card"} clip (a semantic link to composition authoring), and notes the aspect ratio sizes the frame with 9:16 as the safer default for vertical cards.

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?

States a specific verb and resource — render ONE authored card standalone and get the still back as an image — and explicitly scopes it against siblings by naming preview_clip for motion. An agent can distinguish it from preview_clip, preview_component and preview_frame from the text alone.

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?

Gives an explicit when: 'Use this while writing a card — it is the fast loop for catching overflow, collisions, or unresolved tokens.' It also gives the when-not with the alternative named: 'To judge MOTION rather than layout, shell the card with a motion preset and use preview_clip.'

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