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

With no annotations, the description carries the full burden and does so: the kit goes to the pool and is lost if the raid fails, the result is a drand round ~30s later, role bonuses only apply if the admin switch is on (and mainnet stays closed), and no weapons/items are allowed. These are exactly the risky behavioral traits an agent needs before committing funds.

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 with the core action and squad size, then layered with prerequisite, role, and disambiguation detail. Dense but each clause carries operational value; slightly heavy but not padded.

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 4-param mutation with no output schema and no annotations, the description covers the async result path (drand round then resolve), the loss condition, the approval prerequisite, and the role mechanics. Nothing essential to calling 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 real meaning the schema defers to it for: the role id mapping (1 Driver, 2 Hacker, 3 Muscle, 4 Face, 5 Inside Agent, 0 none) and the note that 5 role ids fill only 4 seats. This compensates for the schema's vague 'role ids differ per game' pointer.

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 (prepare, unsigned) and resource (raid on someone else's apartment) with scope (squad of 2 to 4, you first). It explicitly distinguishes itself from the Season 1 crew raid and the older 3-to-5 squad raid, so an agent can tell it apart from prepare_crew_raid and other siblings 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?

Routes the agent to the right follow-ups explicitly: use prepare_raid_resolve for the result, prepare_approve_leader to renew daily approvals. It also sets the prerequisite (each member must have approved you, approval expires after 1 day or the raid is refused) and states when the raid is refused. Clear when-to-use and how it composes with siblings.

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