revert_last_run

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description need not restate those. It adds valuable behavioral context that the tool re-enables paused items and removes negatives the agent added, which goes beyond the schema and helps an agent predict side effects. No contradiction with annotations is present.

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 tight sentences with no filler. The core action is front-loaded in the first sentence, and the second provides essential context ('escape hatch') and concrete effects. Every clause earns its place.

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 the output schema exists, return-value details are not needed. However, the description does not fully compensate for the 0% schema coverage on parameters: customer_id and dry_run are left to inference. The core behavior and when-to-use guidance are solid, but the invocation details are incomplete for a tool with three parameters.

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 0%, so the description carries the burden of explaining parameters. It only addresses run_id implicitly through 'Defaults to the most recent run,' but leaves customer_id and dry_run completely unexplained. An agent cannot know what customer_id scopes or what dry_run does from the description alone.

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 ('a run's changes'), and explains the mechanism ('using the inverse operations stored in the journal'). It also clarifies the default behavior ('Defaults to the most recent run') and frames the tool as an escape hatch, which clearly differentiates it from the many campaign/keyword management siblings.

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 explicitly says when to use this tool: 'when the agent gets something wrong.' It also implies a conditional for run selection via 'Defaults to the most recent run,' suggesting the run_id parameter controls targeting another run. It does not name alternative tools, but no sibling appears to serve the same undo function, so the lack of explicit exclusions is acceptable.

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