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

With annotations covering safety (readOnly=false, destructive=false, openWorld=true), the description adds meaningful context: Desk checks the chain, sends Settle after the review window, and the escrow then pays out. This discloses the downstream consequence beyond what annotations provide, though it's light on failure/retry behavior.

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?

Three short sentences with the trigger condition front-loaded, and no wasted words. Minor narrative flavor ('The escrow pays you then') but it earns its place by explaining the payoff.

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, but the description explains the flow and consequence of calling it, which is enough for an agent to invoke it correctly. It could say more about what happens on chain-check failure, but overall it's adequate.

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 75%, with sig, slot, and session documented in the schema itself; only taskId lacks a description. The prose adds no syntax or format detail beyond the schema, so baseline 3 is appropriate.

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 action (telling Desk the loop delivery is sent) tied to a concrete precondition (MarkDelivered landed). It's distinguishable from siblings like desk_loop_deliver/desk_loop_redeem, though it doesn't explicitly name those siblings.

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 trigger condition: call this after your MarkDelivered transaction lands. The when is unambiguous, though it doesn't contrast with alternatives or state when-not to use.

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