read_sequence_captions

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

With no annotations provided, the description carries the full burden. It transparently discloses the API limitation: 'Premiere Pro exposes no caption-read API in its scripting DOM, so in practice this returns trackCount:0 / captions:[] even when the sequence HAS a working caption track.' It also documents the captionReadSupported:false flag and explains the meaning of a zero result, which is exemplary. No contradictions with annotations.

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?

The description is brief yet information-dense. It front-loads the primary purpose, then explains the critical caveat in the next sentence, followed by an alternative approach. Every sentence adds necessary context; there is no fluff.

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?

Despite having no output schema, the description thoroughly covers the return format, the failure mode, the flag field, and a workaround. It even preempts misuse by clarifying that a 0 result does not mean no captions. This is complete for such a nuanced tool.

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 100%—the only parameter (sequenceId) already has a description in the schema: 'Optional sequence ID. Defaults to the active sequence.' The tool description does not add additional parameter semantics, but none are necessary given the schema is clear. 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?

The description opens with a specific verb+resource+return type: 'Reads caption tracks of a sequence, returning each caption clip as { start, end, text } in seconds.' This precisely states what the tool does and even distinguishes it from reading transcriptions by focusing on caption tracks and their structure.

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 gives explicit guidance: warns that the tool returns empty results in practice and directs to an alternative: 'To read cue text/timing, parse the source .srt file directly instead.' This clearly explains when not to rely on this tool and what to use instead, satisfying the when/alternative criteria.

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