Skip to main content
Glama

Can this agent pay this address, now, this much? (free, advisory)

gate_check
Read-onlyIdempotent

Use this when your client applies a written payment policy (AP2 vocabulary) and wants block, warn, log or allow with every reason; it is not a safety verdict, and we never block. One call before an agent pays: the payee facts, the agent's own context from our ledger (what it paid in the period, how often, whether and when it first paid this payee, how many new payees today), the out-of-character score of this payment as the agent's next, and a decision under a policy written in the AP2 mandate vocabulary (allowed_payees, amount_range, budget {max, period: daily|rolling_24h|rolling_7d}, agent_recurrence, execution_date) plus ours: new_payee {max, window_hours, max_new_per_day, step_up_ratio, step_up_days}, refuse_conditions {fact: block|warn|log|ignore} and signal {v2: {notable, major}}. Anything the evaluator does not understand fails closed. Named policies: log-only (default), balanced, recommended, recommended-v3, strict (their measured cost on 500 real agents is in the policy document). The answer is block / warn / log / allow with every reason, and is recorded (advisory since 1 Nov 2026; the default policy log-only never warns or blocks): we never block anything; your client decides, and decides its own fail mode when we are unreachable. Since 13 Nov 2026 every answer carries a receipt (gate.receipt.v1): the agent, the payee, the amount, the policy name and hash, the decision, the reasons and the time, signed with Ed25519, to keep beside the payment as proof that it was checked first; receipts of checks made with a Desk session are also written into our signed log, which a daily Base transaction commits to (read one back at /api/gate/receipt?id=<decision_id>). A receipt never says a payment was made or that the payee is safe.

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": {
      "agent": "<agent>",
      "payee": "<payee>",
      "amount_usd": "<amount_usd>"
    },
    "name": "gate_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYesThe paying agent: token id, act_8453_N, slug or bound wallet
payeeYesThe 0x address to be paid
policyNoOr your own policy object in the AP2 vocabulary; unknown keys fail closed
amount_usdYesThe amount in USD
policy_nameNoA named policy (default log-only)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior3/5

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

With readOnlyHint/idempotent/non-destructive already declared, the description still adds real behavioral context: unknown policy keys fail closed, the default log-only policy never warns or blocks, results are recorded and signed as gate.receipt.v1, and Desk-session checks enter a signed log. However, it is muddled about enforcement — the answer can be 'block' while 'we never block anything' is repeated three times, and the receipt/log discussion is tangential to making the call.

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 usage trigger is front-loaded, which is good, but the rest is a single run-on block mixing policy vocabulary, named-policy cost claims, effective dates and receipt internals. 'We never block' appears three times and the receipt paragraph is long relative to its decision value. Since there is no output schema the return-format detail is justified, but it should be trimmed and split.

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

Completeness4/5

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

For a 5-parameter, no-output-schema tool, the description covers the essentials: the decision vocabulary, that every reason is returned, fail-closed behavior on unknown keys, the default policy, unreachable-service fail mode, and the receipt payload fields. What is missing is any sense of response shape beyond decision/reasons/receipt and error behavior for malformed agent or payee identifiers.

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

Parameters4/5

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

Schema coverage is 100%, but the richest parameter, the nested 'policy' object, is documented only as 'your own policy object in the AP2 vocabulary'. The description compensates by enumerating allowed_payees, amount_range, budget {max, period}, agent_recurrence, execution_date, new_payee {max, window_hours, max_new_per_day, step_up_ratio, step_up_days}, refuse_conditions and signal.v2. It also names and orders the five policy_name values with the log-only default.

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 description states a specific function: evaluate an agent's prospective payment against a written policy and return block/warn/log/allow with every reason, using payee facts, the agent's ledger history and an out-of-character score. That is clearly a policy gate rather than a safety verdict. It does not name a sibling (e.g. pay_check or payee_facts) to differentiate itself, so it stops short of a 5.

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

Usage Guidelines4/5

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

'Use this when your client applies a written payment policy (AP2 vocabulary)' and 'One call before an agent pays' gives a clear trigger context. The exclusion 'it is not a safety verdict, and we never block' implies where safety checks belong instead, but no alternative tool is named and there is no explicit when-not guidance for the safety-oriented siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.