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

With no annotations at all, the description carries the full burden and delivers real substance: the operation is unsigned (approve-for-exact-kit-price then enter), applications can lose a drand lottery with automatic kit refunds, and the weapons module is inert this testnet round. It omits what the returned payload looks like and whether a prior prepare_approve_leader is required for each member (that detail lives only in the schema), leaving some behavioral gaps.

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?

Purpose, cost mechanics, lottery outcome, crew sizes, and role ids are front-loaded in that order, and every clause carries operational information. It is dense and long, and the trailing testnet note about weapons/city_state.switches is close to tangential, but nothing is pure filler.

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 five-parameter mutation with no annotations and no output schema, the description supplies the game constraints, role encoding, crew-size rules, and the refund fallback — enough to call it correctly. The remaining hole is the transaction lifecycle after preparation (what to do with the unsigned payload), which the description never addresses.

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 genuinely adds meaning: it enumerates role ids 1-6 and notes they match the heist and raid, gives per-game member-size limits, and explains that a Pilot needs no aircraft and only the Muscle carries a weapon. That goes beyond the schema's terse 'convoy or ledger' and 'see this tool's description'.

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?

Opens with a specific verb plus resource ('prepare (unsigned) your crew's application') and immediately scopes it to two games, 'Convoy hit or Ledger job'. An agent can distinguish it from siblings like prepare_job_claim or prepare_vehicle_heist_launch without reading 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?

It states the game scope (convoy/ledger only), the qualifying crew sizes (convoy 1-5, ledger 2-5), required roles per game, and points to prepare_job_refund_kits for the lottery-loser path. It does not, however, say explicitly when to prefer this over adjacent tools or what to call after the unsigned application is prepared, so it stops short of full when/when-not guidance.

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