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

Annotations only declare the safety flags; the description adds the important behaviors: starting is free, preparation takes about a minute, brought clips require the person's confirmation via PrismPoster's card, and an approval_required answer locks the job to what was approved. It doesn't disclose what happens on conflicting inputs (e.g. trend_id plus clip_asset_id) or how failures surface, which keeps it below a 5.

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 concept is front-loaded in the first sentence, followed by the input paths, the approval caveat, then the polling step. Sentences are dense but each carries workflow information; the only real redundancy is repeating the 3-30 second constraint already in from_seconds/to_seconds.

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, the description carries the return burden and does it well: polling get_job yields the cast list with pictures and 1080p/4k pricing. The approval branch and the free-to-start fact round out the lifecycle. It could be more complete by placing preview_remake_cast and remake_render in the pipeline, but an agent has enough to call this correctly.

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%, so every parameter including the 3-30 second range and idempotency_key semantics is already documented in the schema. The description's parameter-level contribution is mostly restatement ('choose 3-30 seconds of it', 'approval_id... other arguments are ignored'), so baseline 3 applies.

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 opens with a concrete definition of what a Remake is (a clip recreated with new performers copying moves, gestures, camera and timing) and then states the specific action: start one. Three distinct entry points are named (Trend, import_media asset, account clip), which distinguishes this from remake_render and remake_trends without opening any 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?

It gives explicit routing rules for the inputs: remake_trends for a Trend, import_media asset_id for the person's own clip, clip_id for a video the account made, plus the 3-30 second window. It also tells the agent the next step is polling get_job. It stops short of naming preview_remake_cast or remake_render as the downstream alternatives, so the workflow isn't fully mapped.

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