production.facial_review

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

Annotations already declare non-readonly, non-destructive, non-idempotent. Beyond that, the description adds genuinely useful behavior: 'facial is the immutable plan.json reference', 'Candidates are new Actions evaluated through NLA tracks', 'the body Action is never modified', and that speech requires explicit timed phonemes or TIMING_INPUT_REQUIRED is raised. Still missing are result/state semantics and whether review gates downstream apply.

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 text is compact but front-loads a non-informative label ('facial_review: M7 facial unit') and strings together jargon-dense clauses in one paragraph. Every clause carries some signal, but the ordering buries the most decision-relevant facts (what it does, what remains unmodified) mid-passage.

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 described. But with 7 entirely undocumented parameters, a mutation-capable tool, and an ambiguous core purpose, the description leaves too much for the agent to infer before a correct call; it explains side-effect boundaries well but not inputs or scope.

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% across 7 parameters, so the description must compensate and largely does not. It explains only that 'facial' is the immutable plan.json reference and repeats the schema's apply default; brief, intent, options, object_name, and operation_id get no meaning at all.

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 a plain verb+resource purpose such as 'review facial animation candidates before acceptance'; instead it opens with the opaque label 'M7 facial unit'. Hints like 'plan first, apply=false by default' and 'Candidates are new Actions' let an agent infer it evaluates candidates, but the actual operation is left implicit, and nothing distinguishes it from siblings like facial_accept, facial_reject, or facial_refine.

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 an ordering convention (review before applying), which is real guidance. However, no alternative tool is named and no condition tells the agent when to pick facial_review over facial_accept/facial_reject/facial_validate_expression, so the guidance remains implied rather than explicit.

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