production.facial_generate_expression

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

Annotations mark it non-read-only and non-destructive; the description adds that apply defaults to false, that candidates are new Actions on NLA tracks, and that the body Action is never modified. That is useful side-effect context beyond the annotations, though it does not cover permissions or failure modes.

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 a single dense semicolon chain. It is not bloated, but the opening identifier and jargon like 'M7 facial unit' and 'Evidence-based semantic mapping' mean it is not front-loaded with a plain purpose statement.

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 7-parameter tool with 0% schema coverage, the description is too thin on parameter meaning and exact operation. It covers non-destructiveness and workflow stage but leaves the agent guessing on most inputs.

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 coverage is 0% for 7 parameters, and the description only touches 'apply' (default false) and 'facial' (immutable plan.json reference). 'brief', 'intent', 'options', 'object_name', and 'operation_id' are left entirely undocumented, so the description does not compensate for the schema gap.

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?

Opens with 'facial_generate_expression: M7 facial unit,' which restates the name rather than plainly stating what it generates. Later clauses ('Candidates are new Actions... the body Action is never modified') imply it creates candidate facial animation from a plan, but the core purpose is never stated directly.

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?

Provides sequencing ('plan first'), a safe default ('apply=false by default'), a speech precondition ('explicit timed phonemes/visemes'), and a boundary ('Technical QA and artistic review stay separate'). It never names the sibling planning or lipsync tools, so an agent must infer the exact alternative.

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