production.facial_deformation_qa

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

It adds substantive behavior beyond the annotations: apply=false by default, facial as an immutable plan.json reference, candidates being new Actions evaluated through NLA tracks, the body Action never being modified, and TIMING_INPUT_REQUIRED for speech. This clarifies mutation scope and safety in a way the annotations alone do 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 dense with semicolon-separated clauses and is information-dense, but the opening 'M7 facial unit' and 'evidence-based semantic mapping' delay the core purpose. Every clause carries some information, yet front-loading and readability suffer.

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 six-parameter tool with 0% schema description coverage and an output schema, the description omits meaning for four parameters and does not fully state the QA criteria. Behavior is partially covered, but an agent would struggle to supply brief, intent, options, or object_name correctly.

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?

Only two of six parameters get indirect meaning: apply has a stated default and facial is described as an immutable plan.json reference. brief, intent, options, and object_name receive no explanation, and schema description coverage is 0%, leaving most inputs opaque.

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 names a 'facial deformation QA' unit and says 'technical QA and artistic review stay separate,' but never plainly states what it checks or what a call returns; 'M7 facial unit' and 'evidence-based semantic mapping' are internal jargon. It is distinguishable as some QA validation, but not clearly from facial_review, facial_validate_expression, or deformation_analyze.

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?

It gives a plan-first/apply=false workflow and a speech-input requirement, but does not say when to use this instead of facial_review, facial_validate_expression, or deformation_analyze. There are no explicit exclusions or sibling-routing instructions.

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