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

Annotations already declare idempotentHint=true and destructiveHint=true, and the description usefully echoes idempotency and discloses the delivery mechanism for large exports. However it never explains why the tool is flagged destructive (what is consumed or overwritten) or how long the resource reference lives, leaving the most consequential behavior undisclosed.

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 tight sentences with the operation stated first and the delivery caveat second; nothing is padded. It is arguably slightly over-compressed given the missing parameter guidance, but there is no wasted text.

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?

An output schema exists, so return values need not be explained, and the 'expiring resource reference' line covers the one non-obvious output shape. Still, for a three-required-parameter mutation-ish tool with zero schema descriptions, the definition leaves format choice, key construction, and the destructive flag unexplained.

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 0% and the description mentions none of the three required parameters. 'Idempotent' loosely gestures at idempotencyKey, but format (six enum values) and the transcriptionId pattern are entirely undocumented outside the raw schema, so the description does not compensate for the coverage gap.

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 gives a specific verb and resource ('Starts an idempotent transcript export') and adds the delivery model, so the agent knows exactly what operation it is invoking. It does not explicitly contrast with related siblings like get_transcript or get_transcript_artifact, which keeps it below a 5.

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?

Usage is only implied: the note that large exports come back as an expiring resource reference hints at a follow-up retrieval step, but the description never names when to call this versus get_transcript/get_transcript_artifact, nor states prerequisites such as a required transcriptionId. An agent must infer the workflow.

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