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

Despite annotations already flagging a non-read-only, open-world mutation, the description adds substantial cost and side-effect context: credits charged on create, refunded on failure, status polling free, quote_only makes nothing and charges nothing. It also discloses that status returns a branded view_url when done — none of which is inferable from the annotations or schema.

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 is front-loaded and the numbered Kling sequence is well structured, but the pricing information is stated twice ("Charges credits on create; failed jobs are refunded" followed by the near-identical PRICE sentence) and the trailing fragment "To run it (not for a quote) send action." is garbled and adds nothing.

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 15-parameter, no-output-schema, multi-step pipeline tool this covers the essentials: which parameters gate which flow, pricing behavior, and what status returns. It still leaves minor gaps — what identify-face hands back (the session_id/face_id mapping) and how long a session stays valid before create must be called.

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 earns above that by explaining cross-parameter semantics the schema cannot — the parameter combinations that select each flow, that timing values are in MILLISECONDS, that sound_file is a base64 data URI, and that volume fields are 0-100 percent.

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?

The opening line gives a specific verb+resource ("Lip-sync audio onto one of your videos") and the body enumerates the three action modes and two engines, so an agent can tell what it does. It does not, however, differentiate itself from the sibling `sync3_lip_sync_video` tool even though it explicitly offers Sync 3 as an engine, leaving real ambiguity about which entry point to pick.

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?

Strong internal routing guidance: it states the default (Sync 3 when no engine/session_id/face_id), when to pick engine="best" vs "kling", the three-step Kling sequence, and to call quote_only:true before running. Missing only external routing — nothing says when to prefer this over `sync3_lip_sync_video`, `talking_avatar_video`, or `dub_audio`.

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