Multiply an ad

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

Adds substantial behavior beyond the sparse annotations: one job per variant requiring get_job polling, same-length output via motion transfer from an image-edited opening frame, removal of burned-in captions, free refusal for sources over 30 seconds, per-variant cost quotes, and dryRun preview semantics. Nothing contradicts the annotations, and readOnlyHint=false aligns with the render-producing behavior.

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?

Information-dense with every sentence earning its place and key constraints front-loaded (purpose, preserved elements, source URL). The single wall-of-text paragraph is harder to parse than structured breaks, but the density is justified by the tool's operational complexity — the length is appropriate rather than bloated.

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?

Comprehensive for a tool with no output schema: it discloses the return shape (plan plus one job per variant), the polling requirement, cost quoting, source constraints, region behavior, and the dryRun flag. An agent has everything needed to invoke it correctly and avoid describing a variant before its URL exists; only the exact contents of the returned plan go unspecified.

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 improves on it by adding concrete source options for the video parameter, a worked regions example (['Berlin','Tokyo']), and the practical dryRun usage pattern (see plan and quote without rendering). The remaining params (axes, count, notes) are left to the schema, which already documents them adequately.

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 ('MULTIPLY') and resource ('a winning video ad') with the exact outcome: N variants that change character, outfit, location, and/or objects while preserving cut, camera motion, pacing, and original audio. The scope is precise enough to distinguish it from siblings like render_ad, plan_variations, dub_video, and clip_video without consulting their schemas.

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 names alternatives and the conditions that select them: post_edit with a trim op for sources over 30 seconds, clip_video is ruled out ('not a trim'), and dub_video is named as the separate translation step. It also identifies valid video sources (previous render, job result, list_library, post_performance/meta_insights) and when to use dryRun:true for a plan-only preview.

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