Generate Video with Replicate

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

Annotations only cover the safety profile (not read-only, open-world, non-idempotent); the description adds the traits that actually matter here — multi-minute latency, ~24h URL expiry, local MP4 download behavior, and the timeout/pending fallback with the follow-up tool named. It also carries an explicit post-success display requirement for the user-facing URL.

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 purpose and latency, then the display requirement, then args and the polling tip. The Args list duplicates the schema field-by-field and could be trimmed, but the total length is justified for an 8-parameter tool with a nontrivial async flow.

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 does the necessary work: it names the return type, points to replicate_generate_image for shape, and explains that local_paths holds .mp4 files when download=true. That cross-tool indirection for the return shape is the one remaining soft spot, but an agent can still call and interpret results 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 already 100%, including the enum, defaults, min/max and the extra_input object, so the Args block largely restates structured data. The only genuine additions — curated model keys, 'not all models support image_url', 'model-dependent' duration, and the advice to raise timeout_ms for long videos — are already substantially present in the schema descriptions.

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 — generate a video clip from a text prompt, optionally image-to-video — and the medium immediately distinguishes it from replicate_generate_image, replicate_generate_audio and replicate_generate_3d. An agent knows what it produces 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?

Gives clear operating context: it is slow (1-5 min), image_url is only usable with supporting models, and when timeout_ms is exceeded the pending=true + replicate_get_prediction polling path applies. It stops short of explicitly ruling out alternatives such as replicate_run_model or replicate_generate_image, so it is not a full when/when-not statement.

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