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

Beyond the annotations (destructiveHint=false, openWorldHint=false) the description adds genuinely new behavior: the quote is non-spending, it carries an expiry, limits are 15s per passage and 30s for selected video plus output, and it is invalidated by input changes. It stops short of describing failure modes (asset ownership rejection, quote reuse via get_recast_quote) and never says whether quotes are persisted or reusable, which matters for a non-idempotent tool.

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?

Dense and front-loaded: capability, input sources, constraints, approval gate, and invalidation rule appear in that order with no filler sentences. It reads as a long run of imperative fragments, though, and the ordering of the passage/limit rules after the asset guidance makes it slightly harder to scan than a grouped constraint list.

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 9-parameter, nested-anyOf pricing tool with no output schema, the definition covers the hard parts: input selection, duration limits, the non-spending guarantee, the expiry, and the approval gate into confirm_recast. What is missing is how the resulting quote is referenced later (get_recast_quote/confirm_recast linkage) and any statement about permissions or ownership checks on the supplied assets.

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?

With 0% schema description coverage the description does real work: it maps the three portrait alternatives (characterId/lookId, assetId, jobId+imageUrl), explains that 'product' is an image asset ID, and stresses independent startSec/endSec per video and per audio passage with fractional seconds preserved. Gaps remain for 'seconds' (the 2s minimum is unstated, though the 30s cap is implied) and for resolution/aspectRatio, whose enums are self-documenting but whose cost or output implications are not mentioned.

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 first sentence names a specific verb and resource ('Prepare a non-spending Recast product quote') and immediately scopes the accepted input forms: characterId+lookId, an owned image asset, or the exact original of a completed Character Builder job. It also names the downstream sibling ('before confirm_recast'), so an agent can separate pricing from spending without opening the schema.

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 routing is given: use list_media or reference import to obtain owned assets, and wait for explicit approval before calling confirm_recast. It also specifies a precondition ('Provide at least one of direction, dialogue, video or audio'), the empty-string convention when only some inputs are supplied, and the rule that any changed input requires a fresh quote.

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