production.facial_classify_rig

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

With annotations already declaring readOnlyHint=false, idempotentHint=true and destructiveHint=false, the description still adds real behavioural detail: dry-run by default, the source facial action is never modified, candidates are written as new Actions on NLA tracks, and speech work raises TIMING_INPUT_REQUIRED without timed phonemes. Only the "Technical QA and artistic review stay separate" sentence is too abstract to act on.

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?

Dense and front-loaded with invariants, and most clauses earn their place, but the opening "M7 facial unit" and the closing line about QA versus artistic review are cryptic filler that costs tokens without guiding invocation.

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 is present so return values need not be described, and the description covers the mutation safety profile, the immutability invariant and the speech precondition well. The remaining gap is sibling differentiation and the semantics of the four non-core parameters.

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 six parameters, so the description carries the burden. It explains the two behaviourally decisive ones (apply defaults to false / plan-first, facial is the immutable plan.json reference) but leaves brief, intent, options and object_name entirely 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?

"M7 facial unit" is internal jargon, but "Evidence-based semantic mapping (never names only)" does convey a specific activity: mapping facial rig semantics by evidence rather than by name matching. That is more specific than the tautological name, though it never says what artefact is classified (rig controls, shape keys, bones) and does not name rig_classify or rig_map_semantics as alternates.

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 a concrete operating pattern and "facial is the immutable plan.json reference" implies a prerequisite input. However no alternatives are named among the many sibling facial_* and rig_* tools, so the agent must infer when this tool is the right one versus facial_map_visemes, facial_prepare_speech or rig_classify.

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