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

Adds real behavior beyond the annotations: synchronous execution, a 10-credit cost, and a zero-credit path for already-enhanced projects (consistent with idempotentHint=true). It does not, however, explain the destructiveHint=true flag — presumably that re-voicing a completed project replaces its existing audio track, which is exactly the consequence an agent should warn a user about.

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?

Front-loaded with the core operation and the SYNC/cost facts, then the two modes. Every sentence carries information, though the voiceId example lists and parentheticals make it dense enough that a reader must parse carefully rather than skim.

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 no output schema, the description does its duty by stating the return ('Re-voiced audio track'), the async/sync nature (SYNC), the cost, and both input paths. What's missing is failure/edge behavior — e.g. what happens if the target project isn't COMPLETED, or whether the original audio is overwritten.

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 100%, so the baseline is 3, and the description goes further by spelling out the required state of projectId ('a COMPLETED project') and enumerating what voiceId accepts (preset names, aliases, raw ElevenLabs ids). The mode-selection guidance for projectId vs r2Key is the genuinely additive value.

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+resource ('Re-voice audio with ElevenLabs speech-to-speech') and immediately names the mechanism, distinguishing it from neighbors like dub_video, swap_upload, or ai_edit_upload. An agent can tell what it does and what it returns without opening the 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?

Explicitly enumerates the two mutually exclusive source modes — projectId (COMPLETED project) vs r2Key (raw clip) — and even routes the agent to the sibling tools that produce each input (create_upload, import_asset_from_url). The credit condition ('0 credits if already enhanced') is stated as a usage decision factor.

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