production.facial_prepare_speech

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds useful operational context: plan-first default, immutable plan.json facial reference, candidate Actions evaluated through NLA tracks, and the body Action not being modified. It does not fully clarify whether setting apply=true changes the safety profile, but the added behavioral detail is substantial.

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 definition is compact, but it is a dense semicolon-chained paragraph packed with unexplained internal jargon such as M7, NLA, and plan.json. The core plan-first and timing requirements are present but not cleanly front-loaded.

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 zero schema description coverage, the description is incomplete: most parameters and their relationships remain unclear, and routing versus sibling facial tools is not addressed. The output schema helps with return values, but the input semantics and usage context are still under-described.

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% for six parameters, so the description must carry the burden. It explains apply's default and that facial is an immutable plan.json reference, and it notes timed phonemes/visemes are required, but it does not define brief, options, intent, or object_name, nor where the required timing data must be supplied.

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 identifies a facial speech preparation step and states that it plans before applying, so the broad purpose is inferable. However, phrases like 'M7 facial unit' and 'evidence-based semantic mapping' are unexplained jargon, and it never explicitly distinguishes this tool from nearby facial speech/lipsync siblings such as facial_generate_lipsync or facial_map_visemes.

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 implies plan-first usage with apply=false by default and notes that speech needs timed phonemes/visemes, which gives some usage context. But it provides no explicit when-to-use/when-not-to-use guidance and does not name alternatives among the many facial planning, generation, and lipsync tools.

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