production.facial_map_visemes

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

Beyond the annotations (readOnlyHint=false, idempotent, non-destructive), it discloses substantive behavior: facial is an immutable plan.json reference, candidates are new Actions evaluated via NLA tracks, and the body Action is never modified. It also surfaces a named failure mode (TIMING_INPUT_REQUIRED), which is real operational context. Minor deduction for unexplained shorthand like 'M7'.

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 information density is high and little is wasted, but the semicolon-chained style and an opaque opening token ('M7 facial unit') bury the lede. A reader must parse the whole paragraph to learn what is actually mapped.

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?

An output schema exists, so return-value detail is not required, and the plan/apply and immutability model are covered well. Still, four of six parameters are undocumented and the tool's position relative to sibling facial tools is unstated, leaving the agent without enough to select it confidently.

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 0% across 6 parameters, so the description must carry the burden. It adds meaning only for `apply` (default false) and `facial` (immutable plan.json reference); `brief`, `intent`, `options`, and `object_name` remain completely undefined in both schema and prose.

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 names the operation ('evidence-based semantic mapping' of visemes) and states the mechanism (candidates as new Actions via NLA tracks), but 'M7 facial unit' is undefined jargon and the core object/resource being mapped to is never stated plainly. It does not distinguish itself from siblings like facial_generate_lipsync or facial_prepare_speech.

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' gives clear plan-vs-commit guidance, and 'Speech needs explicit timed phonemes/visemes (TIMING_INPUT_REQUIRED otherwise)' is a concrete precondition. However, it never says when to choose this tool over the many facial/lipsync siblings, and 'Technical QA and artistic review stay separate' is suggestive but not actionable routing.

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