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?
Annotations already mark it read-only, idempotent, and non-destructive. The description adds sequencing requirements, result contents (cost and reason codes), and no-key/no-cost/latency context — all beyond what annotations provide, with no contradiction.
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 purpose is front-loaded in the first line, followed by compact WHEN/WHEN-NOT/COST/LATENCY sections. Each line carries operational information with no filler.
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?
Despite having no output schema, it names the return concept (OutcomeReceipt) and its key contents (cost, reason codes), explains the prerequisite workflow, and states access cost and latency. For a one-parameter read tool, this covers what an agent needs to call 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 provides only a bare operation_id string with 0% description coverage. The description references a completed operation and implies the ID comes from get_status, but it does not explicitly define provenance or format; for a single self-explanatory parameter this is minimally adequate.
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 clear verb and object — retrieve the final OutcomeReceipt — and scopes it to completed operations. This distinguishes it from get_status by sequencing, so an agent can select it unambiguously.
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?
Explicit WHEN TO USE and WHEN NOT TO USE sections name get_status as the prerequisite/alternative and forbid calling while pending/executing. This is exactly the guidance needed to avoid premature calls.
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.
The core due-diligence tools are clearly distinct: registry verification, sanctions screening, and contract lookup each have separate purposes and boundaries. The only possible confusion is between get_status and get_outcome, but their descriptions clearly separate state polling from final result retrieval.
Tool names mostly follow a snake_case verb_noun pattern such as get_status, preview_cost, screen_sanctions, and verify_company_record. The main deviation is self_test, and verbs vary across get, lookup, preview, screen, and verify, but there is no casing or style conflict.
Seven tools is within the ideal range for a focused MCP server. However, several tools are generic infrastructure utilities rather than company-verification features, so the set is slightly less scoped than it could be.
The company-verification workflow is reasonably covered: legal existence, sanctions screening, and US federal contracts are all available. However, get_status and get_outcome reference async operations that no exposed tool creates, and preview_cost examples mention operations like send_message that are not present in the server, creating dead ends.