undo

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

With no annotations provided, the description must disclose behavioral traits. It only states the action 'undo' without mentioning side effects, reversibility, error conditions (e.g., no annotation to undo), or whether it applies per image. This leaves the agent without knowledge of what changes occur or what the output schema represents.

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 a single, concise sentence that front-loads the action and object. There is no redundant wording or filler, making it efficient for an agent to parse.

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 simple tool with one parameter and an output schema, the description is minimally adequate. However, it lacks behavioral context such as what happens when there is no annotation to undo, whether the operation is idempotent, or how the output schema relates to the action. Given the simplicity, a 3 is reasonable but it could be improved with a note on undo limits.

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 description coverage is 100% – the image_id parameter is fully described in the schema. The description adds no additional meaning beyond the schema, so the baseline of 3 applies. No extra context about the parameter's format or constraints is given.

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 (undo) and resource (last annotation on an image), clearly distinguishing it from sibling annotation tools like add_box or annotate. The scope is unambiguous and matches the tool name.

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 description implies usage after a mistaken annotation, but provides no explicit when-to-use guidance or mention of alternatives such as get_undo_count. It does not explain when undo might be unavailable or how it interacts with other tools.

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