production.facial_create_brief

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

The description adds real behavioral context beyond annotations: candidates are new Actions evaluated via NLA tracks, the body Action is never modified, and 'facial' is an immutable plan.json reference. That partially reconciles with the readOnlyHint=true framing (it never edits existing data), though it is silent on what actually gets written when apply=true. Speech timing failure mode is disclosed; return shape and side effects of applying are not.

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 short and information-dense with no filler sentences, and the dry-run semantics come early. However, the leading 'facial_create_brief: M7 facial unit' fragment wastes the highest-value position on a name restatement and an unexplained internal code.

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. The description covers the workflow invariants (plan-first, candidate Actions, body untouched, speech timing requirement), but with six undocumented parameters and no mention of the brief/intent contract, an agent still lacks enough to construct a correct 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?

Schema coverage is 0% across 6 optional params, so the description must carry the load. It explains only two of them: apply (default false) and facial (immutable plan.json reference). brief, intent, options, and object_name are neither described nor self-evident, leaving the agent guessing at the primary input payload.

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 opening line restates the name ('facial_create_brief: M7 facial unit') and leans on internal jargon ('M7 facial unit') rather than stating a plain verb+resource. The following clauses do reveal the operation (produce an evidence-based facial plan/brief before applying), but the agent has to assemble the purpose from workflow fragments. It never contrasts itself with close siblings such as facial_generate, facial_plan_expression, or animation_create_brief.

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 dry-run-then-apply cadence, and 'Speech needs explicit timed phonemes/visemes (TIMING_INPUT_REQUIRED otherwise)' gives a precondition plus the error it triggers. But there is no explicit statement of when to pick this tool over facial_plan_expression / facial_generate, and no exclusions or prerequisites beyond the speech case.

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