lipsync

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

With no annotations, the description carries the full burden and does well: it discloses the rig prerequisites, the timing model (60/wpm per word, vowels 1.6x), that visemes are stepped keys placed 'lead' ahead of the sound, jaw easing values, nearest-shape fallback for missing visemes, that it ends on rest, and the events emitted (sfx_talk, talk_word, talk_end). It omits what happens to pre-existing keys and whether the operation is destructive, which are relevant for a key-generating mutation.

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?

The core purpose is front-loaded in the first sentence and the remaining detail is dense and largely non-redundant for a complex 12-parameter tool. It reads as a run-on with many parentheticals, which slightly hurts scannability, but little of it is 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?

For a 12-parameter tool with no annotations and no output schema, the description supplies substantial behavioral and parameter context, including fallback behavior and events. The remaining shortfall is the unexplained 'start' and 'replace' semantics and the absence of any mutation/reversibility note.

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%, so the description must supply parameter meaning, and it largely does: text vs phonemes (ARPAbet or viseme letters or [phoneme, seconds]), wpm timing, lead offset, durations defaults, mouth_slot, jaw_bone, events, and animation. The gaps are 'start' and 'replace', neither of which is explained (notably whether replace overwrites existing keys), leaving a few of the twelve parameters undocumented.

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 states a specific verb+resource+output: generating viseme and jaw keys from text or phonemes into an animation. It is immediately distinguishable from siblings like face_clip, rig_face, or gait, which do different face/animation work. An agent knows exactly what artifact this produces.

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?

The description states the rig prerequisite ('any rig with a mouth slot whose attachments are named A E I O U M F L [rest], and/or a jaw bone'), which implies when the tool is applicable. However, it never says when to prefer this over alternatives such as face_clip or add_keys, nor any exclusion. Usage is inferred from constraints rather than routed explicitly.

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