production.facial_plan_microexpressions

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

Beyond the annotations (destructiveHint=false, readOnlyHint=false), the description adds genuinely useful behavior: candidates are new Actions on NLA tracks and 'the body Action is never modified,' clarifying that a non-read-only call is still non-destructive to existing animation. It also discloses a concrete failure mode, TIMING_INPUT_REQUIRED when speech lacks explicit timed phonemes/visemes.

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?

It is compact and front-loads 'plan first, apply=false by default,' but it is a semicolon-joined blob of dense internal shorthand ('M7 facial unit,' 'Evidence-based semantic mapping') where several clauses require domain context to parse.

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 values need not be explained, and the planning/applying relationship is covered. Still, for a 7-parameter tool with no schema descriptions, the missing guidance on what brief/intent/options/object_name/operation_id mean leaves an agent unable to populate most arguments 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 7 parameters, so the description carries the full burden. It only explains apply (default false) and facial (immutable plan.json reference); brief, intent, options, object_name, and operation_id are undocumented in both schema and description, which is a substantial gap.

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 says 'facial_plan_microexpressions: M7 facial unit' and 'plan first,' which implies planning microexpressions, but 'M7 facial unit' is opaque internal jargon. The critical sibling facial_generate_microexpressions is never named or contrasted, so an agent cannot tell from this text whether to plan or generate.

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 a sequencing rule, and 'Technical QA and artistic review stay separate' hints at routing to facial_review/facial_deformation_qa. However, it never states when to use this versus facial_plan_expression, facial_generate_microexpressions, or facial_plan_blinks, leaving the main selection decision to inference.

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