pr_get_sequence

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

No annotations exist, so the description carries the full burden. It helpfully enumerates the returned fields (node_id, name, start/end/in/out, enabled, speed), which compensates for the missing output schema. However, it says nothing about the failure mode when no sequence is active, whether the read is scoped to the active sequence only versus the whole project, or the cost/size of the response on large timelines.

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, front-loaded with what is returned, then the one downstream fact an agent needs. No filler and no redundancy.

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 and no annotations, the description must describe returns and it largely does by listing the clip fields. The remaining gap is the no-active-sequence case and whether the payload is large enough to warrant batching, but for a parameterless getter this is close to sufficient.

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?

Zero parameters, so baseline is 4. The description still adds useful semantics by explaining that node_id in the response is the key consumed by all clip operations, orienting the agent to the contract of the empty-argument call.

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 the specific resource returned: the structure of the active sequence, enumerated as video/audio tracks containing clips with named fields. An agent can tell this is a read of the current timeline state, not a catalog or a mutation. It does not explicitly contrast with sibling tools like pr_catalog, but the resource is unambiguous.

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?

'node_id is what every clip operation takes' effectively tells the agent this must be called first to obtain node_ids before any clip-level operation, which is clear usage context. It stops short of naming an explicit alternative or stating when not to call it (e.g. when no sequence is open).

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