set_river_spline_points

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

Annotations declare destructive/idempotent/non-readOnly, but the description adds substantial behavior beyond them: it synchronizes water spline metadata, RE-READS the spline to prove the write landed, notes that closed_loop is deliberately NOT touched, and warns that malformed point entries are skipped silently. No annotation contradiction; the overwrite semantics are consistent with destructiveHint=true and idempotentHint=true.

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: the core action appears in the first clause, followed by the returns block. It is dense and every element is informative, though the returns block is slightly redundant ('point_count (RE-READ)' vs 'spline_point_count_actual (RE-READ, same value, unambiguously named)') and the heavy uppercase emphasis is a little noisy.

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 spelling out the return fields (point_count, closed_loop_actual, applied) in the description is necessary and well handled, as is the silent-skip and closed-loop caveat. It stops short of full completeness by not stating overwrite-vs-append semantics for existing points explicitly or any permission/context requirements.

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 both parameters (world-point format, the >=2 constraint, the label semantics). The description reinforces the 'ANY water body' interpretation of water_body_label but adds no new syntax or format detail. Baseline 3 is appropriate when the schema carries the load.

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 (set water body spline path from world points) plus the follow-on sync and read-back verification, so the action is unambiguous. It also actively corrects the misleading tool name by clarifying scope ('NOT RIVER-ONLY', works on lakes/oceans). It does not name sibling alternatives (e.g., set_spline_points) to sharpen differentiation, keeping it just short of a 5.

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?

Offers an implied use case with real value: it is 'the only way to give a LAKE its real shoreline' because the factory spline is an arbitrary closed triangle. That tells the agent when this tool matters, but there is no explicit when-not or comparison against the generic set_spline_points / set_landscape_spline_control_point siblings that also manipulate splines.

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