Refund an OPEN/FUNDED/DISPUTED escrow to the payer (exactly-once). Refunding an OPEN escrow is a cancel.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | ||
| escrow_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds the exactly-once guarantee and clarifies behavior for OPEN escrows, which is useful. But with no annotations, it lacks deeper behavioral context such as idempotency, destructive nature, or side effects on escrow status.
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?
Two sentences, no fluff, front-loaded with the primary action. Every sentence adds value.
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 simple tool with an output schema, the description covers eligible states and a key guarantee. It could mention error conditions or side effects more explicitly, but overall it is fairly complete.
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?
With 0% schema description coverage, the description does not explain the parameters. 'escrow_id' is implied by the tool name, but 'reason' is completely unexplained, leaving the agent without guidance on its purpose or usage.
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 'Refund' and the resource 'escrow' with specific states (OPEN/FUNDED/DISPUTED). It distinguishes from siblings like 'release_escrow' by specifying refund to the payer and noting that refunding an OPEN escrow is a cancel.
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 provides clear context for when to use the tool: refunding escrows in specific states to the payer, with an exactly-once guarantee. However, it does not explicitly state when not to use it or mention alternatives like 'release_escrow' for releasing to the payee.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose covering specific lifecycle actions (open, fund, release, refund, dispute) and queries (status, list, audit). No overlap in functionality.
All tools follow a consistent verb_noun pattern in snake_case (e.g., open_escrow, fund_escrow, list_escrows), with no mixing of conventions.
9 tools is well-scoped for an escrow system, covering all necessary operations without excess or deficiency.
Complete lifecycle coverage: open, fund, release, refund, dispute, status, list, audit, plus self-description. Refund also handles cancellation of OPEN escrows, filling a potential gap.