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

With mutating but non-destructive annotations, the description adds genuinely useful behavior: ordered execution and atomic failure ('If any step fails, nothing changes'). That is the key operational trait an agent needs and it is not in the annotations. It stops short of saying whether partial success is reported or whether nested batches are allowed.

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?

Three short sentences, front-loaded with the atomic-undo benefit, then the step structure, then the failure guarantee. Nothing is wasted or repeated.

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 batch orchestrator the description covers atomicity and step shape, but leaves open which action names are legal, how args map to each action, and whether cross-step dependencies are the caller's responsibility. Without an output schema, the return on failure versus success also goes unmentioned.

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?

At 67% schema coverage, projectId and approvalId are already documented in the schema, and the description does explain that each step pairs an action with its args. However, the critical semantic gap remains: 'action' is an unconstrained string and the description points to 'this list' without enumerating valid action names or their arg shapes.

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 states a specific verb and effect: run several actions in order as a single undo step, with examples (move many clips, split several). That distinguishes it from atomic siblings like move_clip or split_clip, though the phrase 'an action from this list' refers to a list the agent never sees here.

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 payoff of batching (one undo step) is clear, which implies when to use this over repeated single-action calls. But there is no explicit statement of when to prefer individual tools, no prerequisite for approval, and no guidance on ordering dependencies between steps.

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