production.facial_mocap_analyze

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

The description adds genuine behavioral detail beyond the annotations: candidates land as new Actions via NLA tracks, the body Action is never modified, and the facial reference is immutable. But it also advertises an 'apply' path ('apply=false by default'), which conflicts with the declared readOnlyHint=true — a real inconsistency an agent could act on wrongly.

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?

Front-loaded with the name restatement and 'M7 facial unit', which spend words without informing selection. The remaining clauses are dense but each carries some signal; the closing 'Technical QA and artistic review stay separate' is a vague process note that does little work.

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 explanation is not required, and the annotations plus description cover the candidate/NLA model. Still, for a six-parameter planning tool with opaque inputs ('brief', 'options', 'intent'), the description leaves the agent guessing about what to supply and what the analysis actually covers.

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 six undocumented, all-optional parameters, so the description must carry the load. It clarifies only 'apply' (default false) and 'facial' (immutable plan.json reference), and alludes to timing input; brief, intent, options, and object_name get no meaning at all.

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 resource area (facial mocap) and gestures at intent with 'evidence-based semantic mapping' and 'plan first', but never states plainly what the tool produces (an analysis? a mapping plan?). Siblings like facial_mocap_map and facial_mocap_retarget are only indirectly differentiated via 'plan first, apply=false by default' and the immutable plan.json reference, so an agent must infer the split.

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' and 'Speech needs explicit timed phonemes/visemes (TIMING_INPUT_REQUIRED otherwise)' give real usage conditions and a hard prerequisite. However, there is no explicit statement of when to pick this over facial_mocap_map / facial_mocap_cleanup / facial_analyze_hybrid, and no 'do not use when' guidance.

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