production.facial_generate_gaze

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

Annotations declare it is a non-destructive mutation, and the description usefully adds that candidates are new Actions evaluated through NLA tracks and that the body Action is never modified. It also clarifies the plan-first workflow and default apply=false. However, the 'Speech needs explicit timed phonemes/visemes' sentence is unrelated to gaze and creates confusion rather than clarity.

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 not front-loaded with a clear purpose; it opens with cryptic labels ('M7 facial unit') and includes a tangential sentence about speech phonemes. Several phrases are vague or do not earn their place, such as 'never names only' and 'Technical QA and artistic review stay separate.'

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?

For a seven-parameter mutation tool with zero schema descriptions and an output schema, the description is incomplete. It explains some behavioral traits (plan-first, non-destructive candidate creation) but leaves the meaning of most parameters and the gaze-generation purpose unclear.

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%, so the description must explain all seven parameters. It only touches on apply ('apply=false by default') and vaguely references 'facial' as the immutable plan.json reference. It says nothing about brief, intent, options, object_name, or operation_id.

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 never states plainly what 'generate gaze' does beyond the tool name. Opening with 'M7 facial unit' and 'Evidence-based semantic mapping (never names only)' is jargon that restates the name rather than specifying the action or its output. It does not distinguish this from sibling tools like facial_coordinate_gaze or facial_generate_saccades.

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?

There is one implicit usage hint ('plan first, apply=false by default'), but no guidance on when to use this tool versus alternatives such as facial_coordinate_gaze or facial_generate_saccades. No exclusions or prerequisites are stated.

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