capcut_undo

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

With no annotations, the description carries the behavioral burden and does a reasonably good job: it discloses a 20-step history limit and that already-saved state is not touched. It does not discuss error behavior or whether the operation can be reversed beyond the stated limit, but the key persistence behavior is surfaced.

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 description is two short sentences, front-loads the operation and scope, and contains no filler. Every clause contributes information about when and how the undo operates.

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 tool with one required parameter, no output schema, and no annotations, the description is incomplete: it never explains what to pass for 'draft' or what the tool returns. The undo semantics are clear, but a caller cannot reliably construct a valid invocation from this text alone.

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?

The single required parameter, 'draft', is a string with 0% schema coverage and is not mentioned in the description. An agent cannot tell whether it is a draft ID, a path, a JSON object, or the content to act on, so the parameter semantics are effectively unknown.

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 clearly states a specific verb ('Undo'), the resource ('the last edit'), and scopes it to the current session with a 20-step limit. It does not explicitly name a sibling alternative, but the persistence qualifier distinguishes it from save/discard 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?

It gives clear context: use this after a mistaken edit in the current session, up to 20 steps back. The statement that saved-to-disk content is unaffected communicates an important boundary, though it does not name alternatives or list exclusion cases such as empty undo stacks.

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