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

Adds context beyond annotations: the operation is 'billable', requires a public HTTPS URL, is asynchronous, and returns a receipt immediately. The cost/billing disclosure is critical and nowhere in the annotations. Combined with destructiveHint/openWorldHint annotations, this is strong coverage.

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, front-loaded with the action, followed by the async receipt behavior. The docs link is a reasonable pointer. No wasted clauses.

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 an output schema and rich annotations covering safety and idempotency, the description is mostly adequate. But for a 4-param tool with 0% schema description coverage, leaving language/displayName semantics unexplained and the idempotencyKey format unclear keeps it from being complete.

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?

Description adds meaning to url ('one public HTTPS media URL'), which is genuinely useful. However, the required idempotencyKey is unexplained (though idempotentHint annotation helps), and language/displayName are entirely undocumented — a real gap at 0% schema coverage across 4 params.

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?

Specific verb+resource: 'starts a billable transcription from one public HTTPS media URL' via the Wisprs jobs API. Clear what the tool does. It doesn't explicitly differentiate from siblings like retry_transcription or get_job_status, but 'starts' implies initiation rather than polling.

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?

Tells the agent this kicks off async work — 'returns a durable operation receipt immediately. The transcript is ready when the operation completes' — which implies subsequent polling. But there is no explicit when-to-use vs. retry_transcription or get_job_status, and no stated prerequisites (account, quota).

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