production.facial_accept

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

Beyond the annotations, the description discloses important behavior: apply=false is plan-only, facial is an immutable plan.json reference, candidates become new Actions rather than modifying the body Action, and missing timed speech data triggers a timing requirement. It does not fully explain permissions or all side effects of an actual apply, but it adds substantial context and does not contradict the annotations.

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 compact with no repeated filler, but it is a dense semicolon chain that front-loads jargon such as 'M7 facial unit' and 'evidence-based semantic mapping' before stating operational constraints. It could be better structured around the primary action and subsequent conditions.

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 need not be explained, and the annotations already establish that this is a non-destructive mutation. However, for a 7-parameter tool with 0% schema coverage, the description leaves too many parameter meanings and the accept lifecycle relative to review/reject/refine tools unclear.

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?

With 0% schema description coverage across 7 parameters, the description must carry parameter meaning, but it only touches on apply and facial. The apply default is already in the schema, and brief, intent, options, object_name, and operation_id are left 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?

The description identifies this as a facial-unit tool and references candidates, immutable plan.json, and new Actions, but it never states a direct verb+resource such as 'accepts a facial candidate' or explains what acceptance commits. It is distinguishable from facial_reject/facial_review only by implication, not by explicit comparison.

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 some usage context: plan first, apply defaults to false, and speech requires explicit timed phonemes/visemes. The line that technical QA and artistic review stay separate hints at boundaries, but it never explicitly says when to choose this over facial_review, facial_reject, or facial_refine, nor what prerequisites must precede acceptance.

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