Retrieve the final OutcomeReceipt for a completed operation.
WHEN TO USE: Use after get_status returns success/failure/partial to retrieve the full result with cost and reason codes. WHEN NOT TO USE: Do not use for operations still in pending/executing state — use get_status first. COST: free - no key required LATENCY: ~50ms
| Name | Required | Description | Default |
|---|---|---|---|
| operation_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds meaningful context: the result includes 'cost and reason codes', and the operation requires a terminal state. The free/no-key and ~50ms latency notes add useful operational behavior beyond the annotations.
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 compact and well structured, with clear section labels ('WHEN TO USE', 'WHEN NOT TO USE', 'COST', 'LATENCY'). Every sentence carries meaningful information, and the critical usage guidance is front-loaded before the operational details.
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?
The description covers purpose, usage conditions, exclusions, cost, and latency. The only minor gap is that it doesn't explain the OutcomeReceipt structure, but since no output schema exists and the tool has a single parameter, the description adequately covers what an agent needs to invoke it correctly.
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?
The schema only defines 'operation_id' as a plain string with no format guidance. The description compensates by clarifying that the operation must be completed and that it's a get-style read, which gives semantic weight to the parameter. With only one parameter and clear contextual usage, this is reasonably helpful.
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 verb ('Retrieve') and a specific resource ('final OutcomeReceipt for a completed operation'), which clearly identifies the tool's purpose. It lacks full sibling differentiation because no sibling tool names are provided, but the 'final OutcomeReceipt' phrasing distinguishes it from get_status.
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?
Provides explicit when-to-use guidance ('after get_status returns success/failure/partial'), an explicit when-not-to-use condition ('pending/executing state'), and an alternative action ('use get_status first'). This is exemplary guidance for an agent.
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.
Most tools target distinct actions, but screen_sanctions and map_trade_restriction both screen parties against OFAC/EU/UK sanctions lists, so the same party-screening request could plausibly route to either. check_compliance also uses a broad 'compliance' name, though its messaging-specific parameters help separate it. The detailed descriptions largely mitigate the ambiguity, but the overlap is real.
Seven of eight tools follow a clear snake_case verb_noun pattern (check_compliance, get_status, screen_sanctions, verify_company_record). self_test breaks the pattern as a noun-style name rather than an imperative verb_noun, but it remains lowercase and readable. Overall naming is predictable and consistent.
Eight tools is a well-scoped size for a compliance/screening service, and each tool has a distinct operational role. The supporting helpers (get_status, get_outcome, preview_cost, self_test) are justifiable parts of the full workflow rather than padding.
Core due-diligence workflows are covered: sanctions screening, trade-restriction mapping, company verification, and messaging-compliance pre-flight. Notable exclusions such as the UN Consolidated List, PEP/adverse media, and bulk screening are explicitly disclosed rather than hidden, so agents can work around them. The gaps are more like optional enhancements than dead ends.