production.facial_generate_jaw

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

Beyond the annotations it discloses meaningful behavior: the facial argument is an immutable plan.json reference, candidates are new Actions on NLA tracks, and the body Action is never modified — which corroborates destructiveHint=false with concrete mechanics. It also documents the TIMING_INPUT_REQUIRED failure mode for speech input. Return values are covered by the output schema, so the remaining gap is minor.

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?

Content is front-loaded but the opening clause ("M7 facial unit") and "Evidence-based semantic mapping (never names only)" consume scarce space with opaque jargon. The semicolon-chained style packs four distinct topics into one block, which is dense but still scannable.

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 7-parameter mutation tool with zero schema descriptions, the definition covers the plan/apply workflow, immutability guarantees, and one error condition — a reasonable skeleton, and the output schema handles return values. It falls short on parameter meaning and on how this unit relates to the other facial_generate_* siblings, which an agent needs to choose correctly.

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% and all seven parameters are undocumented in the schema. The description only clarifies two of them — apply (default false) and facial (immutable plan.json reference) — leaving brief, intent, options, object_name, and operation_id entirely unexplained. With no structured parameter help, the description must compensate more than it does.

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 description leads with "M7 facial unit", an internal label that conveys nothing about what is generated (jaw curves, shape keys, an Action?). It never states plainly that this produces jaw animation data, so the agent must infer the purpose from the tool name alone; the remaining sentences describe mechanics rather than the operation itself. Nothing distinguishes it from siblings like facial_generate_brows or facial_analyze_jaw.

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?

"Plan first, apply=false by default" implies a plan-then-apply workflow, and the speech clause gives one concrete prerequisite (explicit timed phonemes/visemes, otherwise TIMING_INPUT_REQUIRED). However, no alternatives are named — an agent cannot tell from this text whether to reach for facial_generate_lipsync, facial_generate_coarticulation, or facial_generate for the jaw-related cases. Usage is implied rather than directed.

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