Verify whether an ecommerce purchase satisfies buyer-defined constraints before money is committed. Returns PASS, FAIL, or REVIEW with supporting evidence.
Scored across 1 tool
With a single tool there is no possibility of misselection; verify_purchase has one clear purpose stated precisely.
The lone tool follows a clean verb_noun snake_case convention with no competing styles to clash against.
A single tool is thin for a verification service; supporting operations like listing or configuring buyer constraints feel missing, though one focused entry point is defensible for a narrow purpose.
The core check (PASS/FAIL/REVIEW with evidence) is covered, but there is no way to define/manage buyer constraints, inspect purchase records, or retrieve prior verification results, leaving notable gaps.
Check whether a proposed ecommerce purchase satisfies buyer-defined constraints before money is committed. Returns PASS, FAIL, or REVIEW with supporting evidence. Use REVIEW when evidence is incomplete, ambiguous, conditional, stale, or conflicting.
| Name | Required | Description | Default |
|---|---|---|---|
| merchant | No | ||
| product_url | Yes | ||
| buyer_region | No | ||
| requirements | Yes | ||
| buyer_country | Yes | ||
| buyer_postal_code | No | ||
| transaction_facts | No | ||
| product_or_scenario | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and does a solid job: it discloses that evaluation happens pre-commitment and enumerates the three result states with the condition that triggers REVIEW. It does not state whether the call is purely read-only/no-side-effect (implied but not asserted), nor anything about latency, auth, or whether external merchant lookups occur.
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 tight sentences with the core purpose front-loaded, followed by outcome states and the REVIEW trigger. No filler, and every sentence carries decision-relevant information.
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?
An output schema exists, so return values need not be explained, but the tool takes 8 parameters including two unconstrained nested objects with 0% schema coverage and the description offers no guidance on them. For a tool whose entire value hinges on how 'requirements' and 'transaction_facts' are shaped, this is a material 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 0% across 8 parameters, so the description must compensate and largely does not. Only 'buyer-defined constraints' loosely maps to the free-form 'requirements' object; the other open-ended object ('transaction_facts'), plus product_url, buyer_country, buyer_region, merchant, and buyer_postal_code, receive no explanation of expected format or content.
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 and resource ('Check whether a proposed ecommerce purchase satisfies buyer-defined constraints') with a clear decision framing ('before money is committed'). The three possible outcomes (PASS, FAIL, REVIEW) are named, so an agent knows exactly what class of result this tool produces. No siblings exist to differentiate from, but the tool's scope is unambiguous.
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 clear usage context ('before money is committed') and a precise condition for the REVIEW outcome ('evidence is incomplete, ambiguous, conditional, stale, or conflicting'), which is genuinely actionable routing guidance. It lacks any exclusions or named alternatives, but there are no sibling tools to route toward.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
verify_purchase
