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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered, and the description adds real behavioral context: the card is replaced by another card tool in the same reply, and the user's selection arrives as a single natural-language message ('Use the Whiteboard look with Marcus as the narrator'). It does not describe ordering, pagination or what happens if the card is dismissed, so it adds value but not a complete behavioral picture.

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 paragraph is front-loaded with what the card shows and dense with useful content, with no filler sentences. However, the middle clause ('then, in the same card, the narrator...') is convoluted and the whole thing would read better split into short lines for card behavior, response shape and constraints.

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?

There is no output schema, and the description compensates fully by describing exactly what the card renders and the shape of the reply the user will send back. For a zero-required-parameter card tool this covers everything an agent needs to invoke it correctly and not duplicate the listing itself.

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 100%, with all three parameters documented including the short/long enum and the picked look id, so the baseline is 3. The description only indirectly touches the parameters by mentioning 'this format' and the 'own:...' id convention; it adds no new syntax or selection semantics beyond the schema.

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 states a concrete action and resource: it renders the ClipFlux setup card containing the look list (own looks with 'own:...' ids, then all format-specific ClipFlux looks with real covers) and the narrator list. It also differentiates from siblings by naming quote_look and design_look as the tools that create a new own look, so an agent can distinguish this from get_look or list_voices.

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?

Explicit rules are given: call it on its own and wait, because another card tool in the same reply replaces this card, and never list, describe or invent looks or voices yourself since these are the only ones. The alternative path for creating a look is routed to quote_look and design_look, so both when-to-use and when-not-to-use are covered.

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