execute_payout

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

Annotations already declare destructive=true, idempotent=true, openWorld=true, but the description adds substantial non-structured context: human approval gating, at-most-once execution, the rule that a chain receipt alone never proves bank credit, and the reconciliation requirement for uncertain submissions. It is consistent with idempotentHint rather than contradicting it.

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 dense sentences, front-loaded with the core action and approval requirement, followed by safety constraints. Every sentence earns its place, though the wording is terse to the point of being clipped.

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 destructive, open-world mutation tool with no output schema and a single fully-documented parameter, the description covers approval, at-most-once execution, retry/reconciliation, and credit-claiming semantics. It does not describe failure/error behavior or what an agent should report back after execution, leaving a small gap.

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 100% and the payoutId description already carries the key guidance ('never create a replacement to retry'). The description adds no parameter-level syntax or constraints beyond what the schema states, so the baseline 3 applies.

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+resource (execute a prepared payout) with the crucial qualifier 'at most once' and the approval step. An agent can immediately distinguish it from prepare_payout (which produces the quote) and from payout_status (which only inspects).

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?

Explicitly defines the retry/repeat semantics ('Repeated calls inspect the existing payout'), the reconciliation requirement for uncertain submissions, and the prohibition on resending. It does not explicitly name payout_status or payout_history as alternatives for pure inspection, but the context is clear enough to route correctly.

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