pr_getSequenceState

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description correctly focuses on behavior beyond that: clip indexes are 1-based and are unstable across edits, requiring a re-read. That instability warning is genuinely useful context an agent would not get from structured fields. It stops short of noting output size or performance for large sequences.

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?

Everything is packed into one front-loaded sentence that leads with the app and resource before the payload, plus a short imperative caveat. No filler sentences, though the dense parenthetical enumeration is harder to scan than a short bulleted list would be.

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 carries the full burden of describing the return value, and it does so field by field down to clip-level attributes like source in/out, speed, and media path. For a 2-parameter read tool with strong annotation coverage, nothing essential is missing beyond a note on the includeMarkers flag.

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 50%, with only the sequence parameter documented and includeMarkers left bare. The description reinforces the sequence semantics ("active (or named)") but mentions markers only as returned data, giving no hint that includeMarkers toggles whether markers appear in the result. It partially compensates for the coverage gap but does not close it.

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 names the exact resource (active or named sequence) and enumerates precisely what the call returns: frame size, fps, duration, playhead, in/out, tracks with clips, and markers. That makes the tool unmistakably a sequence-state read, clearly distinct from pr_getProjectState or pr_getClipProperties in scope, though it never names those siblings explicitly.

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?

One real usage cue is present: "Clip numbers change after edits: re-read", which tells the agent when to call it again. There is no explicit statement of when to prefer pr_getSequenceState over pr_getClipProperties or pr_getProjectState, and no guidance on when not to use it, so usage is implied rather than spelled out.

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