production.facial_analyze_eyelids

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

The description adds meaningful operational context beyond annotations: candidates are new Actions evaluated through NLA tracks, the body Action is never modified, and facial is an immutable plan.json reference. It also notes that apply defaults to false and that speech requires explicit timed phonemes/visemes, though the latter is not clearly relevant to eyelid analysis.

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 description is dense and front-loads the tool name, but several sentences read as generic facial-unit boilerplate. The speech/phoneme requirement and the QA/review separation are unlikely to earn their place in an eyelid-analysis definition.

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?

Given six parameters, 0% schema coverage, and a complex facial workflow, the description is incomplete. It conveys the plan/apply and candidate-action model, but never explains what the eyelid analysis checks, what inputs like brief/intent/options mean, or how this differs from adjacent facial analyzers.

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% and the description only explains apply and facial in any detail. It leaves brief, intent, object_name, and options undocumented, which is a substantial gap for six parameters.

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 mostly restates the tool name with opaque jargon: "M7 facial unit" and "Evidence-based semantic mapping (never names only)" do not explain what eyelid analysis actually does. It does not distinguish this tool from siblings such as facial_analyze_eyes, facial_plan_blinks, or facial_generate_lid_follow.

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?

It states a plan-first workflow and that apply defaults to false, but gives no guidance on when to use this analysis versus related facial tools. There are no exclusions or alternatives named, so an agent has to infer selection from the tool name alone.

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