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

Goes well past the annotations by disclosing immutability (every edit yields a new timeline_id), the 24-hour retention window after last use, and what identifiers the call returns. These are exactly the lifecycle facts an agent needs and none are in the structured fields.

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?

Four short sentences, each doing distinct work: purpose, return values, lifecycle semantics, and long-running-work guidance. Purpose is front-loaded 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?

Lifecycle and return behavior are well covered, and the output schema handles return shape, but for a tool whose only required argument is a nested sequence spec the description leaves that side entirely unexplained. Adequate for calling it, thin for calling it correctly on first try.

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 only 33%, and the description says nothing about any parameter — not the required nested `sequence` (width/height/fps), nor `name`, nor how `tracks` counts map to the returned track ids. The heaviest documentation burden falls on the schema alone.

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 ("Start an empty timeline") and immediately names the sibling interactions it pairs with (timeline.get, timeline.load), so an agent can distinguish it from the many clip/track tools in the sibling 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?

Gives a concrete routing rule: for work longer than a day, persist the timeline.get document and restore via timeline.load. That effectively covers when to prefer an alternative workflow, though it does not say when not to create a fresh timeline at all.

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