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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=false and idempotentHint=false; the description goes further by explaining the refusal-on-conflict rule, the shared undo stack with the user's own ⌘Z, and that only the latest step is reversed. Its claim that "a retry of the same call does not undo twice" sits at the edge of idempotentHint=false (call identity vs. re-invoking with the same arguments), so the disclosure is valuable but slightly ambiguous rather than a clean 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?

Dense but front-loaded: undo/redo scope first, then step definition, then conflict/refusal behavior, then the include_others caveat and retry note. Every sentence carries information, though the repetition of "take back" phrasing and the retry sentence add some length.

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. For a destructive, non-idempotent mutation the description covers scope, reversibility limits, conflict handling, and the authorization-flavored include_others condition; the only real gap is not mapping the `redo` parameter explicitly.

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 only 33%: storyboard_id and redo carry no schema descriptions. The description compensates for include_others (echoing and reinforcing the schema's warning) but never ties the prose word "redo" to the `redo` boolean or explains storyboard_id's role beyond its uuid format. Partial compensation at best.

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 first sentence states a specific verb+resource+scope: undo (or redo) of the agent's own last gesture on a film/storyboard. It defines "gesture" concretely (contiguous writes from one tool call = one step) and is clearly distinct from siblings like edit_storyboard or delete_storyboard, which are not reversible history operations.

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?

Explicit when-to-use and when-not: it refuses when the person or Studio assistant has changed the board, and include_others should be set "only when the user asked you to take their change back," with a direct instruction to set it only in that case. The redo path is also framed as an alternative behavior of the same call.

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