production.facial_plan_blinks

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

Annotations already flag this as non-read-only and non-idempotent, and the description adds real operational context beyond them: the default is a dry run (apply=false), candidates land as new Actions evaluated via NLA tracks, the body Action is never touched, and speech inputs require timed phonemes/visemes. This meaningfully de-risks invocation, though 'immutable plan.json reference' and 'M7' remain unexplained.

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 opens by restating the tool name and an opaque unit code, then chains semicolon-separated jargon fragments. Some clauses carry weight (apply default, body Action untouched), but 'Technical QA and artistic review stay separate' and 'Evidence-based semantic mapping (never names only)' consume space without actionable meaning.

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 plan/apply workflow plus non-destructive candidate mechanics are covered. However, for a 7-parameter tool with 0% schema coverage, leaving five parameters (intent, options, object_name, brief, operation_id) unexplained is a real gap for an agent trying to call it 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% across 7 parameters, so the description must carry the load. It only clarifies two: apply (defaults false, plan-first) and facial (an immutable plan.json reference). brief, intent, options, object_name, and operation_id are left entirely undocumented in both schema and description.

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 implies planning blinks, but the description never states plainly that it produces a blink plan/action for a facial rig. Instead it leads with opaque taxonomy ('M7 facial unit') and jargon ('NLA tracks', 'plan.json reference'), and it never distinguishes itself from close siblings like facial_generate_blink 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' hints at a plan-then-apply workflow, and the speech clause hints at a prerequisite. But there is no explicit statement of when to use this tool versus facial_generate_blink, facial_plan_expression, or facial_accept/reject, and no conditions or exclusions are given.

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