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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the crucial post-state semantics beyond that — the parent is superseded by its children, the children must be decided afterward, and nothing is deleted. This explains the mutation's effect and its reversibility, precisely the kind of context structured fields do not carry.

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 short sentences, front-loaded with the action and trigger, followed by outcome and reversibility. Every sentence earns its place; the final clause is slightly redundant with 'the parent and its children are all retained' restating 'nothing is deleted,' but it is efficient 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?

No output schema exists, so the description must convey the result state — and it does, explaining that the parent is superseded and children are retained. Combined with the post-step instruction, an agent has enough to invoke correctly; only the interaction with sibling decision tools is left implicit.

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 the schema already documents clusterId, customerId, and conditionKey fully. The phrase 'one more condition' reinforces that conditionKey introduces an additional split dimension, but the description adds no syntax or validation detail beyond the schema. Baseline 3 is appropriate.

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 by one more condition') and frames the domain clearly via 'undecided cluster', which ties it to the adjudication/review flow among siblings like get_adjudication_queue and record_review_decision. An agent can tell what it operates on and what it produces without opening the 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 an explicit trigger condition: use it 'when its members are not actually one behavior.' It also states the follow-up workflow ('decide on the children afterwards'), which is genuine usage guidance. It stops short of naming alternative tools (e.g. record_review_decision) explicitly, so it is clear context but not full when-vs-alternatives routing.

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