production.facial_plan_expression

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

Adds real behavior beyond the annotations: candidates are new Actions evaluated through NLA tracks, the body Action is never modified, apply is off by default, and untimed speech raises TIMING_INPUT_REQUIRED. The 'body Action never modified' statement usefully corroborates destructiveHint=false and clamps scope. It still doesn't say what a failed plan returns or how the immutable facial plan.json is versioned.

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 front-loaded with the tool's role and the key plan/apply distinction, but it is a run-on semicolon chain mixing workflow, data model, error codes, and process philosophy. 'M7 facial unit' and 'Evidence-based semantic mapping (never names only)' consume space without helping an agent choose or call the tool.

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 description covers the planning-versus-apply semantics and the speech-timing precondition. However, it leaves over half the parameters undefined on a tool with zero schema coverage, which is a substantive gap for a 7-parameter call.

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?

With 7 parameters and 0% schema description coverage, the description must compensate fully. It explains only two: 'apply' (default false) and 'facial' (immutable plan.json reference). 'brief', 'intent', 'options', 'object_name', and 'operation_id' are undocumented in both places.

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 name-to-description link ('plan first', candidate Actions) makes clear this produces a facial expression plan rather than applying it, but 'M7 facial unit' is internal jargon that conveys nothing to an agent. It does not distinguish itself from close siblings such as facial_generate_expression, facial_plan_blinks, or facial_plan_microexpressions.

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 hints at a sequencing relationship, but no alternative tool is named and no exclusion or prerequisite is stated explicitly. An agent must infer when to pick this over facial_generate_expression or facial_create_brief.

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