loot_settle_opens

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

With no annotations, the description carries full responsibility. It discloses that the operation is permissionless, requires LOOT_AGENT_PRIVATE_KEY to send transactions, credits loot to the requesting wallet, and skips settled/unpublished requests. This covers key trait implications (mutation, auth, idempotency) beyond what annotations might provide. Minor gap: no mention of return format, but not critical for a mutation tool.

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 terse sentences, each adding distinct information: purpose+permissions, invocation options, skip behavior, and key requirement. No fluff, front-loaded with the core action. Every sentence earns its place.

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?

Given the tool's complexity (mutation, optional params, drand dependency, permissionless), the description covers the essential points: when to use, how to invoke, key requirement, and side effects. It does not detail output format or error conditions, but with no output schema and the described specifics, it is sufficiently complete for an agent to call it correctly.

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 67% (wallet and scan_last have descriptions; ids does not). The description adds value by explaining the relationship between ids and scan_last ('Pass ids, or let it scan the newest requests') and defaults for scanning. This clarifies parameter usage beyond the schema's bare properties, partly compensating for the coverage gap.

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 clearly states the verb 'Finish' and resource 'pending box opens', and explains the permissionless nature of submitOpen. It distinguishes from siblings like loot_open_box (initiation) and loot_claim_loot (claiming) by focusing on the settlement step, though it does not explicitly name alternatives. This is specific and actionable.

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?

Provides clear usage context: settle when drand round is published, and options to pass ids or scan newest requests. It also notes skipping of settled requests and unpublished rounds, which defines when the tool is applicable. It does not explicitly mention when to use an alternative tool, but the conditions are well-articulated.

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