Get transcript file

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

readOnlyHint=true already covers the safety profile, and the description adds real value on top: returns file text (not a parsed structure), timing is in source-video seconds, and words:true only affects VTT word timestamps. It doesn't mention failure behavior when no transcript exists, which is the one behavioral gap for a retrieval tool.

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 the output format and segmentation, then the words/format behavior, then the sibling pointer. Nothing is redundant with the schema or annotations.

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 does the job of describing what comes back (file text, one cue per segment, source-video seconds). Complete for the happy path, though it never says what happens if the project has no transcript or is still processing, which matters in a pipeline with wait_for_project and reanalyze_project siblings.

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%, so the baseline is 3, but the description adds semantics the schema lacks: that cue timing is expressed in source-video seconds, and that the words flag produces a per-word <timestamp> marker in the cue rather than a separate field. That clarifies intent beyond the enum/default documentation.

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 a specific verb+resource (get the project transcript file) and pins the output form: SRT or WebVTT subtitle file, one cue per segment, in source-video seconds. It explicitly distinguishes itself from the closely named sibling get_transcript by contrasting file-based subtitles with plain timed lines.

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?

'Use get_transcript to read it as plain timed lines instead' names the alternative and the condition that selects it, so an agent can route between the two transcript tools without opening either schema. The subtitle-file vs timed-lines distinction is the exact decision an agent faces here.

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