production.animation_accept_generated

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

Adds context beyond the annotations: dry-run by default (apply=false), the generation must be an immutable plan.json reference, source Actions are retained (non-destructive), and unsupported adapters fail with concrete errors. These are useful behavioral disclosures the readOnly/destructive hints alone do not convey.

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?

Dense but front-loaded around the plan-then-apply workflow. Some clauses, notably "high-level M6 unit" and "technical QA and temporal artistic review are distinct," cost space without giving an agent an actionable instruction.

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 mutation default is covered. Still, for a 7-parameter optional-everything mutation tool the description leaves the core effect of "accept" and four parameters undefined, which is not 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 coverage is 0%, so every parameter depends on the description, and it only explains apply, generation, and options; brief, intent, object_name, and operation_id are unmentioned. The partial explanations it does give (plan.json reference, options carrying stage thresholds/visual review) are substantive but leave half the surface undocumented.

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 never plainly says what "accept" does to a generated animation (finalize, commit, mark approved?) — it opens with the opaque phrase "high-level M6 unit." Nothing distinguishes it from sibling animation_reject_generated, which is the natural alternative an agent must choose between.

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" and "Explicit mapping and compatible body rig required" give real preconditions and a two-step workflow. However, it never names reject_generated or states when acceptance is appropriate versus rejection, so the routing to a sibling is left implicit.

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