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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write nature is known. The description adds real value beyond that: it writes a NEW derived alignment while the source stays, it returns a task (async), the result carries disruption_summary/retention_pct, and missing inputs yield CLARIFICATION_REQUIRED. It does not explain reversibility or permissions, nor does it explicitly reconcile the 'destructiveHint=true' annotation with the claim that the source stays.

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?

A single front-loaded paragraph that opens with the operation and cardinality, then requirements, then side effects and error behavior. Dense but every clause carries information; slightly crammed into one block rather than separated.

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 15-parameter destructive write operation with an output schema, the description covers purpose, required inputs, TS-source alternatives, async task semantics, clarification behavior, and the key result field. What remains thin is sibling differentiation against territory_rebalance/territory_merge and the meaning of the balancing/repair knobs.

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 only 7% and the schema marks nothing as required, so the description carries heavy load — and it does supply the de facto requireds (source_tal_id, target_territory_id) and the alternative TS-source params, plus the dwell_time/workload link. However, roughly half the parameters (repair_policy, balance_tolerance, disruption_weight, part_layer, point_layer, new_tal_label, new_territory_label, visit_frequency_field) get no explanation, so compensation for the coverage gap is only partial.

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 (split one territory into two) and encodes the cardinality change as '(N to N+1 territories)', which cleanly distinguishes it from the sibling territory_merge and territory_rebalance without opening their schemas. The intent to minimize changes to the rest of the alignment is also stated.

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 clear preconditions: needs source_tal_id and target_territory_id, plus a Territory Solution via one of three alternatives (map_session_id / ts_handle / ts), and notes dwell_time is required for workload balance. It also states fallback behavior (CLARIFICATION_REQUIRED with the question). It does not explicitly say when to prefer this over territory_rebalance or territory_merge, but the scope statement effectively routes the agent.

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