undo

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

With no annotations provided, the description carries the full behavioral disclosure burden. It explains the side effect (broadcast event causing open views to update), the no-op case (returns ok: false with nothing_to_undo), and the scope limitation (view states are not affected). This is rich, non-obvious behavior.

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 compact sentences cover the purpose, the broadcast side effect, the error case, and the exclusions. Every sentence adds necessary information, and the core action is front-loaded.

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?

Given zero parameters and an output schema, the description sufficiently covers operation, effects, error handling, and non-targets. It stops short of explaining whether multiple successive undos are supported, which is a minor ambiguity for an undo tool.

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 tool has zero parameters, so the baseline is 4. There are no parameter semantics to clarify, and the description appropriately focuses on behavior rather than inventing unnecessary parameter guidance.

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 uses a specific verb (revert) with a clear resource (the last graph change) and enumerates the affected operations (push/update/delete/clear/cite/import). It clearly differentiates from the redo sibling by describing the inverse of a graph mutation.

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 clearly states when to use the tool: to revert the last graph change. It also explicitly excludes view-state changes (filter/style/focus/snapshot), which helps the agent avoid misusing it, though it does not explicitly name redo as the alternative for reapplying changes.

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