get_transcript

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

With no annotations provided, the description carries the full burden — and it delivers. It discloses the stitching/mapping behavior, return segment structure, coverage info semantics, the ok:false failure condition when clips aren't transcribed, the always-present activeSequence field, and the edge case of the user switching sequences mid-session. This is exemplary disclosure for a tool with zero annotation support.

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?

Five sentences, all earning their place: purpose, segment shape, coverage info, optional windowing, prerequisite/failure mode, and the activeSequence contract. The core purpose is front-loaded. Minor redundancy exists in repeating 'sequence-time'/'sequence-relative' variants, but there is no bloat for a tool with no output schema to fall back on.

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 tool with no annotations and no output schema, this description is remarkably complete. It covers the return contract (segment fields, coverage info, activeSequence), the prerequisite and failure mode (ok:false), parameter semantics, and even a cross-call usage pattern for detecting sequence switches. Nothing an agent needs to invoke it correctly is missing.

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 100% — both startSec and endSec already have descriptions in the schema ('Filter to segments overlapping [startSec, endSec]'). The description adds the useful clarification that the window is in sequence-time, but otherwise reiterates what the schema states. Baseline 3 is correct since the schema does the heavy lifting.

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 ('Get the active sequence's transcript') and immediately distinguishes the tool's unique behavior — stitching across all audio source clips and mapping into sequence-time. It clearly differs from siblings like get_active_sequence (which returns only the sequence object) and find_words (which searches within transcript data).

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?

Clear context is provided: the tool reads transcript data for the active sequence, can be windowed, and the description even recommends comparing activeSequence across calls to detect mid-session sequence switches. The prerequisite (clips must be transcribed in Premiere first) and failure mode are explicit. However, no alternative tools are named and no when-not-to-use conditions are stated.

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