Export a transcript

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses the payment model: segment-level export is free, word-level timed export (word_level:true) is a paid unlock. It also notes that DOCX/PDF are unavailable, setting correct expectations. 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?

Three sentences, each serving a purpose: first states core function, second adds pricing context, third clarifies missing formats. No unnecessary words or repetitions. Front-loaded with the most critical information.

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 simple export tool with strong annotations (readOnly, idempotent, non-destructive), the description covers the essential: what it exports, in which formats, with timing details, pricing nuance, and exclusions. No output schema is needed as the returned file content is implied. Completely adequate given the tool's complexity.

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 low (33%, only word_level has a description). The description compensates by listing format values (SRT, VTT, TXT, MD, JSON) and explaining word_level's cost implication. job_id is not explicitly described but is self-explanatory as the identifier of the transcript to export. Overall, adds some meaning but not comprehensive.

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 clearly states the verb 'Export' and the resource 'a finished transcript', listing specific output formats (SRT, VTT, TXT, MD, JSON). It distinguishes from siblings like 'get_transcription' (which likely returns the raw transcription object) by focusing on file export with caption timings. The mention of 'DOCX/PDF are available in the Pepys web app' further clarifies the tool's scope.

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?

The description implies usage when a transcript is finished and a file format is needed. It provides relevant context: segment-level export is free, word-level is paid, and DOCX/PDF are not available via this tool. However, it does not explicitly state when not to use it or compare to alternatives like 'get_transcription' or 'search_transcript'.

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