production.facial_analyze_curves

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

With readOnly/idempotent/non-destructive already in annotations, the description adds real behavioral context: candidates are new Actions evaluated through NLA tracks, the body Action is never modified, facial is an immutable plan.json reference, and speech work raises TIMING_INPUT_REQUIRED. That is meaningful disclosure beyond the structured annotations, though framed in dense jargon.

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?

It leads with the tool name restated and then packs several loosely related clauses into a short span; information is present but heavily jargon-laden and not cleanly front-loaded by what matters most to an agent (what is analyzed).

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 needn't be explained, and annotations carry the safety profile. However, for a 6-param analysis tool with 0% param coverage and vague domain terms, the description leaves too much implicit about inputs and scope to be fully adequate.

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 6 params, so the description must compensate. It clarifies apply (default false) and facial (immutable plan.json reference), but says nothing about brief, intent, options, or object_name, leaving most parameters undocumented in both schema and description.

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 verb+resource come only from the tool name; the body never states plainly that it analyzes facial animation curves or what the analysis yields. Phrases like 'M7 facial unit' and 'Evidence-based semantic mapping (never names only)' are internal jargon that don't let an agent distinguish this from the many facial_analyze_* siblings (jaw, lips, eyes, bones, etc.).

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 workflow default, and 'Speech needs explicit timed phonemes' gives one conditional. But there is no when-to-use guidance versus the dozens of facial analysis siblings, and no explanation of when to set apply=true.

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