Undo

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

Goes well beyond the annotations: it discloses the undo granularity (one MCP edit call, including an ae_batch, equals one step), the failure behavior when nothing is undone, and the return payload of count plus a cross-comp change report. This is exactly the mutation-and-failure context an agent needs before committing.

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 tight sentences, front-loaded with what the tool is, followed by granularity, failure mode, and alternatives. No filler and no repetition of the schema.

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?

There is no output schema, yet the description states what is returned (steps undone and a change report across all comps) and what happens on failure. Nothing an agent needs to invoke this correctly is missing.

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 already documents the 1-50 range and early-stop behavior, so the schema carries the load. The description still adds real meaning by explaining what counts as a single step and that a multi-step undo yields an aggregate change report.

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 ('Undo the last action(s) in After Effects') and anchors it to a familiar UI analog ('Edit > Undo'). It also defines the unit of an undo step, which no sibling tool does, so an agent can distinguish it from ae_checkpoint and ae_redo.

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?

Gives explicit routing: use ae_redo to reverse this, restore an ae_checkpoint to go back further, and ae_call to reach ae_redo. It also states the precondition that After Effects must have something undoable and no modal dialog open.

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