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

Annotations already declare the write/cost/destructive profile and idempotency. The description adds genuinely new context with 'billable' and the 'completed' prerequisite, but leaves the async nature implicit — it 'starts' something yet never says a job is created and must be polled.

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?

A single tight sentence: verb, cost note, precondition, and target format all front-loaded with no filler.

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 no explanation, but for a billable, asynchronous, idempotent mutation the description omits job-tracking behavior, what idempotencyKey dedupes, and any confirmation of what 'completed' means.

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 0% across three required parameters. The description clarifies only targetLanguage (BCP-47) and hints at transcriptionId; idempotencyKey — a required 16-128 char key with a regex — is never explained, so the description does not compensate for the schema 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?

States a specific verb and resource ('starts a ... translation of a completed transcript') plus a target, which clearly separates it from summarize_transcript and repurpose_transcript. It doesn't name a sibling explicitly, so it falls just short of 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?

'completed transcript' implies a precondition (the source must already be transcribed), but there is no explicit guidance on when to choose translation over repurpose_transcript or summarize_transcript, and no mention that the started job must be tracked via get_job_status.

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