Start a multi-scene film

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

Annotations already declare non-read-only, non-idempotent, open-world behavior, so the bar is lower, and the description still adds real context: background/asynchronous execution, the returned pipelineId and the polling step, and an external dependency (ffmpeg). It omits the safety-relevant confirm requirement, keeping it from 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?

Three tight sentences, front-loaded with the core action, then chaining/join behavior, then return value and dependency. Every sentence adds distinct information with no filler.

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 complex pipeline tool with 8 params, nested scene objects, and no output schema, the description covers async flow and return value well, but omits the mandatory confirm=true safety gate, the shared-vs-scene override precedence, and the 30-scene cap. Adequate but with clear gaps.

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 63%, in the middle band. The description's chain/concat explanation largely restates what the schema already documents for those two params, and it is silent on name, scenes, shared, crossfade, and outputDirectory. Baseline 3 is appropriate.

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: generating a multi-scene film scene-by-scene in the background, chaining frames and joining into one MP4. It routes the agent to the correct sibling for follow-up (poll axcel_sequence_status), making it distinguishable from axcel_generate_video and axcel_sequence_list.

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 implies the async usage pattern clearly by saying the tool runs in the background and to poll axcel_sequence_status, which is genuine workflow guidance. However, it never contrasts this with single-scene tools like axcel_generate_video, nor states prerequisites such as the required confirm=true flag, so the when/when-not routing is only partial.

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