production.facial_generate_brows

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

Beyond the annotations, the description discloses that candidates are new Actions on NLA tracks and that the body Action is never modified, which is valuable non-destructiveness context not in the schema. It also warns that speech requires explicit timed phonemes/visemes (TIMING_INPUT_REQUIRED), a concrete precondition, though the phrasing is generic boilerplate shared across the facial family.

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 a dense string of semicolon-separated jargon fragments ("M7 facial unit," "Evidence-based semantic mapping") that lead with a tautological title restatement instead of the core action. Several clauses read as policy boilerplate that does not help invoke this specific 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?

For a 7-parameter mutation tool with zero schema descriptions, the description leaves most inputs undefined and never explains what a candidate output looks like or how apply interacts with options/brief. An output schema exists, so return values need no explanation, but the input-side gaps are substantial.

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 carry the burden, yet it only touches two of seven parameters: apply (reiterating the default) and facial (described as "the immutable plan.json reference"). brief, intent, options, object_name, and operation_id are left completely unexplained.

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 opens by restating the tool name ("facial_generate_brows: M7 facial unit") rather than stating a verb+resource like "generates eyebrow animation." The only functional statement is indirect ("Candidates are new Actions evaluated through NLA tracks"), and nothing distinguishes it from siblings such as facial_generate_expression, facial_generate_jaw, or facial_generate_blink.

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 minimal sequencing guidance, but there is no explicit when-to-use vs alternatives, no prerequisites, and no routing cues among the many facial_generate_* siblings. The closing line about QA and artistic review is boilerplate that does not help an agent choose this tool.

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