translate audio for preview

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds material context: this is a paid job, a new idempotencyKey bills again, an uncertain response must be retried with the identical key, and translation must not be repeated when attaching the output failed or recoveryRequired is true. That is real cost and recovery disclosure beyond the flags. It stops short of stating rate limits or permissions, hence not a 5.

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?

Purpose and scope are front-loaded in the first sentence, and nearly every subsequent sentence carries an operational constraint rather than filler. It is dense — a single long paragraph mixing routing, project rules, idempotency and recovery — so a slight structural cost, but the length is justified by the tool's cost and complexity.

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 paid, destructive, multi-step job tool the description covers prerequisites, project provenance, idempotency protocol, return shape and recovery paths. It even summarizes the return fields (id, status, outputMediaUrl, error, recoveryRequired) despite an output schema existing, which is redundant but harmless and reinforces the polling handoff.

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 workflow-level meaning: idempotencyKey must be persisted before the call and reused only for recovery, and projectIntent=explicit must accompany the project id with a prohibition on inferring intent from matching names or an open editor. Those behavioral constraints go beyond what the property descriptions convey on their own.

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 ('Start one paid job that translates a saved audio asset's speech into another language') plus the output ('translated audio the user can review before a separate lip-sync'). It explicitly names the two siblings it is not — dubbing_create for one-step dubbed video and speech-previews_create for script-based speech — so an agent can route without opening any schema.

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?

Gives explicit when-to-use ('user wants to hear the translation first or place the audio on a timeline') and when-not (one-step dubbing), plus prerequisites: confirm source audio, target language and the estimate quote; create a project via projects_create with defaultWorkflow translate_and_dub; use an existing project only on explicit user selection. It also routes follow-up to translation-previews_get wait:true and jobs_wait, and states that lip-syncing is a separate approved call.

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