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

With no annotations, the description carries the disclosure burden and does well: it names the 10-credit cost, discloses the asynchronous job nature requiring wait_for_video polling, and mentions live preview behavior in app-capable hosts. It stops short of saying what happens on failure or whether credits are refunded.

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?

Four tight sentences, front-loaded with the core action and mode selection before cost, routing and polling hints. No filler or restatement of the title.

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?

Covers the essentials for a 7-parameter async generation tool with no output schema: cost, polling, voice sourcing, and dual input modes. Missing only edge-case behavior such as failure/refund handling and validation limits already visible in the schema.

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; the description adds value beyond it by explaining where voiceId comes from (MiniMax presets, Eleven v3, cloned voices via list_voices) and by framing voiceId/transcript versus audioUrl as alternative input paths.

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 ('Turn a portrait into a talking-head video') and names the underlying engines (AI Avatar Maker, SkyReels V3). The two operating modes (transcript+voiceId vs audioUrl lip-sync) make it clearly distinct from siblings like create_video, create_influencer or create_motion_control.

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 routes the agent to list_voices for voice selection and to wait_for_video for polling, and explains the condition selecting each of the two audio modes. It does not state when-not-to-use it (e.g. versus create_video for non-avatar footage), so no exclusions are covered.

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