Plan motion reveals

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

readOnlyHint=true already marks this as safe, but the description adds real context: it is offline, never contacts AE, never applies edits, and the audit phase deliberately proposes nothing. Those constraints are not derivable from the annotation alone. It does not disclose return shape, but with no output schema that is a moderate gap rather than a contradiction.

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?

Four short sentences, each carrying information: purpose, phase flow, non-mutation guarantee, and the readback prerequisite. The 'Supply real readback and render before/after' prerequisite is front-loaded enough, though it is terse and could be clearer about what input field it refers to.

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 single-parameter, deeply nested planner with no output schema, the definition covers the essential contract: it plans, it does not execute, and it requires verified AE measurements because it cannot inspect comps. Missing only a hint about what the returned plan/ops look like, which is minor given the tool's clearly bounded scope.

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 100% and the nested spec object is self-documenting, so the baseline is 3. The description adds meaning by mapping intent onto the 'phase' field (prepare / reveal / audit) and by flagging that frame values must come from live AE readback, which the schema also reinforces — useful but largely redundant with structured data.

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?

States a specific verb+resource ('Offline motion planner') and scopes it to the concrete asset types (typography, panels, icons, bars). It also implicitly separates itself from the mutating ae_* siblings by saying it never contacts After Effects, though it never names ae_workflow_plan or ae_edit 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?

The phase sequence ('Prepare pivots, reread positions, then request reveal ops') and the note that the audit phase 'checks camera samples without proposing edits' imply when each mode applies. It stops short of naming alternatives or stating when NOT to use the tool for planning versus asking ae_workflow_plan/ae_edit.

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