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

With no annotations, the description carries the full burden and does well: it discloses that the call is unsigned, that cancels refund everyone, that the outcome resolves via a drand round roughly 30s later, that part of each stake is lost on a miss, and that a Safehouse, cooldown or Burner Phone can block the raid. It does not state what the unsigned payload contains per action or what errors look like beyond the blockers.

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 compressed: a one-line mechanics primer followed by an action list with conditions, then the blocking conditions last. Every clause carries information, though the dense run-on phrasing and jargon ('Tricks:', 'drand round') slow parsing slightly.

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 5-parameter, 5-action tool with no annotations and no output schema, the description covers state transitions, permissions, stake bounds, timing and failure blockers — enough to call it correctly. The only gap is what each prepare call returns (the unsigned transaction shape), which an agent must infer from the 'prepare' naming convention.

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 already 100%, so the schema documents every parameter and the baseline is 3. The description adds real value by mapping parameters to actions (crewId + stakeZeni for open, raidId for join/cancel/launch/settle) and giving the 1,000–100,000 stake bounds, but most of that is restated from the schema's own per-field descriptions.

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?

The description names a specific verb and resource — prepare (unsigned) one step of a squad raid on a rival crew — and defines the mechanic (3–5 wallets, equal stake, partial loss on a miss). It never distinguishes itself from the similarly named siblings prepare_raid_launch / prepare_raid_claim / prepare_raid_resolve, so an agent must infer which raid system is which.

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?

Each action carries explicit conditions: open needs crewId + stakeZeni, join approves the stake, cancel is leader-anytime / anyone-after-a-game-day, launch requires leader plus 3+ in squad, settle is anyone after the round. That is strong when-to-use guidance, but there is no 'use X instead' routing to the sibling raid tools.

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