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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the bar is lower. The description still adds real value: it discloses that execution is synchronous ('runs in the request rather than in the background'), that the result reflects actual outcome, and that there is a restorability constraint.

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 tight sentences with zero padding, front-loaded with the core action before the runtime and precondition details. Every clause carries information an agent needs to decide or invoke.

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?

With no output schema, the description partially compensates by noting the result reports what actually happened, and all preconditions are covered. Minor gap: it does not indicate what a failed unmerge looks like or the shape of the returned records list.

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 100% and both parameters are documented in-schema, including the 'Call list_crm_connections first' sequencing hint for connection_id. The description's mention of the 'Merged' status requirement merely repeats the group_id schema description, so it adds no parameter meaning beyond the schema.

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+resource+effect: 'Undo a merge: restore the records it absorbed and return the group to Reversed.' The state transition to 'Reversed' makes it unmistakably distinct from siblings like approve_duplicate_group or get_duplicate_group without needing to open their schemas.

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 explicit preconditions: only works on a group in 'Merged' status and only while absorbed records are still restorable. This tells the agent when the call will succeed or fail, though it names no alternative tool for the opposite action.

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