loot_sell

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

With no annotations, the description carries full behavioral burden. It discloses the one-time approval, exact quote, refusal on unprotected floor, fixed gas, private key requirement, and that selling burns the game position. This is strong transparency, though it omits details like revert behavior, fee implications, or what happens on failure.

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 dense and front-loaded with the core action, then enumerates the two amount modes and the security/approval behavior. Every clause adds value, though it could be tightened by removing the 'Fixed 5,000,000 gas' and 'Needs LOOT_AGENT_PRIVATE_KEY' which are operational constants but not strictly necessary for basic invocation.

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 mutation tool with 5 parameters and no annotations or output schema, the description covers the essential flow (approve, quote, refuse) and the safety constraint, but it does not explain what the function returns (e.g., transaction hash, success message), how errors surface, or whether the token must come from loot_list_tokens. Some gaps remain for an agent to invoke correctly without external knowledge.

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 only 40% (percent and amount_tokens have descriptions), and the tool description clarifies the mutual exclusivity of those two, which is helpful. But it does not explain slippage_bps (basis points meaning), deadline_seconds (until when), or the token address (which specific LOOT token). The description partially compensates but leaves key parameter semantics to inference.

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 tool sells a LOOT token for ETH via a router, and mentions the two input modes (amount or percent). The action is specific and distinguishable from the buy/sell session, but it does not explicitly contrast with loot_buy or other siblings, so it's not a full 5.

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 is obvious from the verb 'sell' when to use this tool, and the description gives the operational sequence (approve, quote, refuse). However, it does not state when NOT to use it (e.g., buying with loot_buy), nor does it suggest alternatives like loot_quote for pre-sell quotes. Usage context is implied but not explicitly scoped.

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