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

Annotations declare a non-readOnly, non-idempotent write, but the description adds material behavior beyond them: writes at the pool's price now, validates the kind's field before any mutation, costs 3 units and a heavy slot, and enumerates the refusal conditions (id not open, cash short for add, missing field per kind). This is exactly the extra context annotations cannot 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?

Highly dense with no filler and front-loaded with purpose before mechanics. It does read as a long semicolon-chained run-on, which slightly hurts scannability, but every clause carries information.

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 6-parameter tool with nested objects and no output schema, the description covers returns (position and cashUsd), side effects, cost, and failure modes. Nothing an agent needs to invoke it correctly is missing.

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%, so the baseline is 3, but the description adds genuinely new semantics the schema lacks — the behavior of each kind enum value (claim pays waiting fees to cash, compound reinvests, add puts amountUsd in, withdraw takes pct of every rung, rebalance re-lays the band from plan, auto sets autopilot rules) and which field each kind requires. That is meaningful meaning beyond the structured fields.

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 ('Changes one of the caller's open paper positions') and immediately scopes it against siblings by naming arena_state for the id and arena_close for ending a position. An agent can distinguish this from arena_open, arena_close and arena_state 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 explicit prerequisites ('Use after arena_state for the id'), an explicit exclusion with the alternative tool ('to end a position use arena_close'), and per-kind guidance on what each kind does. When-to-use is fully covered.

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