Skip to main content
Glama

mt_shopping_verify

Read-only

Verify a shopping transaction against a BuyerAgentCredential by checking its signature, spend limits, and trust score, then return a verification receipt with approval status.

Instructions

Verify a shopping transaction against a BuyerAgentCredential.

Checks the credential signature, spend limits, trust score, and returns a verification receipt with approval status.

Args: credential_jws: JWS compact serialization of the BuyerAgentCredential transaction_amount: Transaction amount (e.g. 189.99) transaction_currency: Currency code (e.g. "USDC") merchant_id: Merchant identifier string item_description: Description of the item being purchased

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "credential_jws": "<credential_jws>",
      "transaction_amount": "<transaction_amount>",
      "transaction_currency": "<transaction_currency>",
      "merchant_id": "<merchant_id>",
      "item_description": "<item_description>"
    },
    "name": "mt_shopping_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
merchant_idYesMerchant identifier string
credential_jwsYesJWS compact serialization of the BuyerAgentCredential
item_descriptionYesDescription of the item being purchased
transaction_amountYesTransaction amount (e.g. 189.99)
transaction_currencyYesCurrency code (e.g. "USDC")

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.3.1
    • addedInput schema / properties / credential_jws / description
      Added value: +"JWS compact serialization of the BuyerAgentCredential"
    • addedInput schema / properties / item_description / description
      Added value: +"Description of the item being purchased"
    • addedInput schema / properties / merchant_id / description
      Added value: +"Merchant identifier string"
    • addedInput schema / properties / transaction_amount / description
      Added value: +"Transaction amount (e.g. 189.99)"
    • addedInput schema / properties / transaction_currency / description
      Added value: +"Currency code (e.g. \"USDC\")"
  2. First observedv1.2.0

TDQS

A3.5/5.0
Behavior4/5

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

With readOnlyHint=true already covering the safety profile, the description still adds real value by disclosing the internal checks performed (signature, spend limits, trust score) and the fact that a receipt is returned with an approval status. The main undisclosed behavior is whether the returned receipt is persisted server-side and whether a denial is surfaced as a returned status or an error, which matters for an enforcement-style tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first two sentences are well front-loaded and dense with useful information, but the trailing Args block is pure redundancy against a 100%-covered schema and could be cut. The purpose statement and the checks list are the only parts that earn their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists, so return-value explanation is not required, and the description covers inputs plus the verification logic. However, for a security-critical gate, it omits how failures manifest (rejected vs. receipt with denial status), whether trust-score thresholds are configurable, and the credential-issuance prerequisite, leaving meaningful operational gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are already documented. The Args block in the description merely repeats the schema strings verbatim ("Transaction amount (e.g. 189.99)", "Currency code (e.g. \"USDC\")") and adds no new semantics such as amount precision handling, accepted currency set, or JWS format constraints, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb ("Verify") and resource ("a shopping transaction against a BuyerAgentCredential"), and the follow-up sentence enumerates what is actually checked (signature, spend limits, trust score). The "shopping" domain qualifier plus the named credential type lets an agent separate it from mt_fantasy_verify, mt_skill_verify, or mt_salesguard_verify by domain, though the description never explicitly contrasts them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the reader infers this belongs in a purchase flow before settlement, but nothing states when to call it versus mt_shopping_info or mt_shopping_issue_vc. There is no mention of the prerequisite that the BuyerAgentCredential must already have been issued, and no exclusion guidance (e.g., what to do if verification fails).

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