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

With no annotations at all, the description carries the whole burden, and it does add one genuinely non-obvious behavioral fact: crossfade/smooth_blend re-shifts the incoming clip to stay anchored to the outgoing clip's end. That is real value. It omits other mutation-critical behavior though — that expectedVersion is an optimistic-concurrency token, what happens on a version conflict, whether the change is undoable, and any upper bound on duration.

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?

Two sentences, no filler, and the core purpose is front-loaded before the crossfade-specific caveat. Every clause carries information an agent would not otherwise have.

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 destructive-ish mutation with zero annotations, no output schema, and 0% schema coverage on four required params, the description does too little. An agent still cannot tell how to obtain or use expectedVersion, what a failure looks like, or whether duration has a ceiling.

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 0% across four required parameters, and the description only clarifies durationMs (unit is ms) and implicitly identifies transitionItemId via 'existing ... transition.' projectId and especially expectedVersion remain completely undefined in both the schema and the description, which is a significant gap for a concurrency-controlled write.

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 gives a specific verb and resource: 'Change how long an existing fade, crossfade or smooth_blend lasts, in ms.' The word 'existing' implicitly separates it from timeline.add_transition and timeline.remove_transition, though no sibling is named outright, so an agent must infer the boundary rather than being routed to it.

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 makes clear this only applies to transitions that already exist and enumerates the three affected types, which is useful scoping. But there is no guidance on when to prefer this over timeline.remove_transition plus timeline.add_transition, and no mention of prerequisites such as obtaining expectedVersion from project.get_state before calling.

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