scamgate

Overview Schema Source Related Servers Discussions Admin

check_payment

Read-onlyIdempotent

Verify a payment for scam risk before sending funds, returning allow, ask, or deny with a risk score and plain-English reasons.

Instructions

Check a payment before making it. Returns a verdict: decision (allow | ask | deny), risk_score 0-100 and plain-English reasons. If the decision is ask, stop and show the reasons to the human. If deny, do not proceed. Results are advisory, not a guarantee.

Input Schema

Name	Required	Description
`amount`	Yes	Amount to pay.
`budget`	No	The spending limit the human gave for this task.
`method`	Yes	card, bank_transfer, crypto, gift_card or other.
`currency`	Yes	e.g. EUR, GBP, USDT.
`payee_name`	Yes	Who is being paid.
`vop_result`	No	Verification of Payee result, if available.
`context_text`	No	The messages or page text that led to this payment.
`is_new_payee`	No	True if this payee has never been paid before. scamgate checks your payee history rather than taking this on trust.
`payee_account`	Yes	IBAN, wallet address, merchant id, etc.
`bank_details_changed`	No	True if the payee's account details changed recently.

Output Schema

Name	Required	Description	Default
`reasons`	No
`summary`	Yes
`advisory`	No		scamgate is advisory. It can miss scams and flag legitimate actions; a human should make the final call on anything flagged.
`decision`	Yes
`warnings`	No	Notes about the check itself, e.g. a stale feed cache
`risk_score`	Yes
`checked_host`	No	For links: the host scamgate judged, the one a browser would open. If it isn't where you expected the link to go, treat that as a warning. Empty for payments and unreadable links.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.3Oct 26, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety bar is met; the description adds the decision protocol the annotations can't express and an honest caveat that results are advisory, not a guarantee. It also makes clear this is a check, not the payment itself, consistent with readOnlyHint.

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

Conciseness5/5

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

Four short sentences, front-loaded with purpose then the outcome-handling rules, with zero filler. Every sentence changes agent behavior.

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

Completeness5/5

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

An output schema exists and the description still names the key verdict fields so the agent can act without a separate lookup. For a 10-parameter, 5-required tool with annotations plus an output schema, nothing needed to call it correctly is missing.

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% and 10 parameters are fully documented in-schema, so the baseline applies. The description adds no extra semantics about required vs optional fields or how context_text/budget influence the verdict.

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

Purpose5/5

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

States a specific verb and resource ('Check a payment before making it') and immediately defines the output shape (decision/risk_score/reasons), so an agent knows exactly what it gets. It is unmistakable next to siblings check_url and update_feeds, which operate on entirely different resources.

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

Usage Guidelines5/5

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

Gives an explicit precondition ('before making it') plus branching instructions on the result: stop and show reasons on 'ask', do not proceed on 'deny'. This is the when-to-use and when-not-to-proceed guidance most tools omit.

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

Deploy Server