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

With no annotations, the description carries the full burden and does real work: it discloses permissionless settlement, that the winner is a public drand draw nobody controls, and the 24-hour void/refund outcome. It omits operational behavior an agent would want — what the 'unsigned' artifact actually is, gas/fee expectations, and error modes if called before the bell.

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?

Four short sentences, each carrying distinct information (what it does, who may call, why it matters, what happens on expiry), with the core action front-loaded. No filler or restatement of the name.

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 and no annotations, so the description should cover the prepare→sign→submit flow, which it does not — it never says what the prepared transaction is or how it gets broadcast. Gameplay and timing context is strong, but the invocation mechanics are left implicit.

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 0% with two required params, so the description must compensate. 'Fight whose bell has rung' maps to fightId, but wallet is genuinely ambiguous for a permissionless settle — is it the caller/payer or a participant? That is an important unresolved detail for a transaction-preparation tool.

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 and resource — preparing (unsigned) the settlement of a fight whose bell has rung — and implicitly separates itself from prepare_fight_claim by noting 'Settling is what lets winners claim.' An agent can distinguish settle vs. claim vs. boost 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 a clear precondition (bell has rung) and a permission note ('Anyone may settle'), plus the expiry boundary — more than a day past the bell voids the fight and refunds everyone. It does not name an alternative tool explicitly or state what to do instead when the fight is already settled or voided, so it falls short of a 5.

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