Redo

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

Goes well past the annotations by disclosing EXPERIMENTAL status, undocumented QE DOM reliance, step-by-step undo-stack verification, and the crucial limitation that the timeline itself is not read back and a matching stack position 'cannot prove which action is on top.' This is rich behavioral context an agent cannot get from the annotations.

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?

Front-loads the EXPERIMENTAL caveat and packs a lot of precise meaning into a small space. The heavy parentheticals and semicolon clauses make it dense, but every sentence carries operational information.

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 high-risk experimental mutation tool, the description covers the QE dependency, the verification model, the guard semantics, and the marker-reversal caveat, and an output schema exists so return values need not be explained. Nothing essential is missing for correct invocation.

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 already 100%, so the baseline is 3, but the description adds semantic meaning: 'count' should match the count used in the paired undo call, and 'expected_undo_stack_index' is a safety guard that refuses without change. This adds context beyond the field-level schema text.

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 ('Redo') and resource (most recently undone Premiere project action(s)), and explicitly grounds it in the QE DOM (qe.project.redo / undoStackIndex). It visibly distinguishes itself from the sibling 'undo' by describing the restore-the-undone-action relationship.

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 a clear usage condition and names the alternative: 'To restore a tool call undone with undo, pass the same count.' It also states when the operation refuses (marker boundaries) and how acknowledge_untracked_markers changes behavior, though it does not spell out explicit when-not scenarios beyond those refusals.

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