production.animation_add_overlap

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and the description is consistent: 'Source Actions retained' and 'generation is the immutable plan.json reference' explain the non-destructive staged model. 'Unsupported adapters return concrete errors' adds error behavior. But the plan-vs-apply workflow and what 'apply' mutates is only hinted at.

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 text is short but dense with unexplained jargon ('high-level M6 unit', 'declared stage parameters') and semicolon-chained clauses, so it is terse without being informative. The plan-first rule is not front-loaded and competes with decorative phrasing.

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 described. But for a staged, non-idempotent mutation with 7 undocumented parameters and a prerequisite rig/mapping, the description omits what overlap does, what it produces, and how the plan/apply cycle proceeds — too much is missing to call this complete.

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 7 parameters, so the description must carry the burden. It mentions apply, generation, and options ('declared stage parameters, thresholds or visual review'), but brief, intent, object_name, and operation_id are entirely unaddressed. Partial compensation leaves significant gaps.

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 essentially restates the name: "animation_add_overlap: high-level M6 unit". It never explains what 'overlap' means operationally or how it differs from close siblings like animation_add_follow_through, animation_refine_generated, or animation_polish_curves. 'High-level M6 unit' is unexplained jargon that adds no clarity.

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 clear sequencing rule, and "explicit mapping and compatible body rig required" states a prerequisite. However, it never routes the agent against alternatives (e.g., when to use add_overlap vs add_follow_through or the generate/refine chain), so selection guidance is implied at best.

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