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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description earns credit by explaining concretely what that means — the parent is superseded by its children and nothing is deleted, so all records are retained. It does not disclose failure modes, idempotency, or the superadmin constraint (that detail lives only in the schema), but the retention/supersession semantics are genuinely additive beyond the annotations.

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?

Front-loaded with the action and condition, and free of filler. The third sentence ('Reversible in the sense that nothing is deleted — the parent and its children are all retained') is slightly belabored, restating non-deletion twice, but it is short enough overall.

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 three-parameter mutation with a rich schema, no output schema, and annotations covering the safety profile, the description supplies the trigger, the state change, and the retention guarantee. What is missing is what the call returns (e.g., child cluster IDs) and whether repeated splits are idempotent, but these are minor gaps given the schema and annotations.

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%, so clusterId, customerId, and conditionKey are already fully documented, including the constraint that conditionKey must be a splitConditionKey taking multiple values. The description's phrase 'one more condition' loosely reinforces conditionKey but adds no new syntax or constraint beyond the schema, so the baseline 3 applies.

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 and resource ('Split an undecided cluster') plus the splitting dimension ('by one more condition') and the motivating condition ('when its members are not actually one behavior'). An agent can distinguish this from record_review_decision or decide_approval without opening any schema.

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 a clear trigger ('when its members are not actually one behavior') and follow-up guidance ('decide on the children afterwards'), which tells the agent this is a precursor to a decision, not the decision itself. It never names the alternative tools or states when NOT to split, so it falls short of full routing guidance.

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