loot_open_box

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

With no annotations, the description carries full behavioral burden, and it succeeds: it discloses the key expenditure, pile reduction, drand round waiting, beacon fetching, on-chain settlement, key-source fallback logic, and the need for LOOT_AGENT_PRIVATE_KEY. It also states the reported outcome (tier counts and loot minted). This is comprehensive for a mutating tool and exceeds typical transparency.

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?

The description is a dense but single-paragraph with no wasted words. It front-loads the core action and proceeds sequentially. Slightly long due to process details, but every sentence adds context. Could be broken into bullets for clarity, but for a single-sentence approach it is efficient.

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 complex on-chain operation with no output schema and no annotations, the description covers the process well but omits key parameter semantics (especially the required token) and does not mention optional parameters or defaults. It also doesn't state that the tool requires a token input, which is the only required field. The agent understands the flow but lacks parameter-level specificity, leaving room for invocation errors.

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 0%, so the description should explain each parameter. While it mentions 'chosen tier' and 'key source', it does not explicitly map to the tier, token, and key_source parameters. The token parameter is required but completely undefined in the description; key_source's enum values are not explained beyond 'auto' behavior. This leaves the agent to infer parameter meanings from schema alone, which is insufficient given zero coverage.

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 states a specific action (open loot boxes), describes the resource (loot boxes, keys, pile), and outlines the multi-step process: spending keys, waiting for drand round, fetching beacon, settling on-chain. This clearly distinguishes it from siblings like loot_settle_opens (which handles settlement separately) and loot_buy/sell. The purpose is unambiguous.

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?

The description explains the mechanics but gives no explicit guidance on when to use this tool versus alternatives such as loot_settle_opens or loot_claim_keys. It implies usage when the agent wants to open boxes, but does not state conditions, prerequisites, or alternatives. The key-source auto behavior hints at configuration, but not usage context.

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