Skip to main content
Glama

Check policy compliance (dry run)

check_policy_compliance
Read-onlyIdempotent

Evaluate a planned purchase against spend policy before submission to get an auto-approve, require-approval, or deny decision plus every rule checked, with no card issued or human notified.

Instructions

Evaluate a purchase against the spend policy without submitting it. Returns the decision (auto_approve, require_approval or deny) and every rule that was checked. No card is issued and no human is pinged.

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_id": "<agent_id>",
      "task_id": "<task_id>",
      "task_goal": "<task_goal>",
      "vendor_domain": "<vendor_domain>",
      "amount": "<amount>",
      "is_recurring": "<is_recurring>"
    },
    "name": "check_policy_compliance"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountYesAmount to spend, in major units of the currency (e.g. 15.00).
task_idYesIdentifier of the task this purchase serves, e.g. '102'.
agent_idYesStable identifier of the calling agent, e.g. 'invoice-bot'.
currencyNoISO 4217 currency code.USD
reasoningNoOptional step-by-step reasoning that led to this purchase. Stored in the audit log.
task_goalYesWhat the agent is trying to accomplish and why this purchase is needed.
is_recurringYesTrue if this creates a subscription, trial that auto-renews, or any repeat charge.
vendor_domainYesMerchant domain, e.g. 'pdfocr.io'.
alternatives_attemptedNoFree or already-owned options the agent tried first, and why they failed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so the description's added value is in disclosing the outcome space — the three possible decisions (auto_approve, require_approval, deny) and that every checked rule is returned — plus the explicit guarantee that no card is issued and nobody is notified. It does not cover what the caller should do on a deny or require_approval decision, which is the remaining behavioral gap.

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?

Three short sentences, front-loaded with the core action, then the return shape, then the safety guarantees. No redundant restatement of the title and nothing that fails to earn its place.

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 nine-parameter tool with no output schema, the description usefully explains the return values (decision enum plus all rules checked), so the agent knows what to expect. It leaves out side effects of subsequent steps and error behavior, but the core completeness requirement is met.

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 all nine parameters carry descriptions (amount units, vendor_domain format, reasoning stored in audit log, etc.), so the schema already does the heavy lifting. The description adds no parameter-level meaning beyond the schema, which is the expected baseline here.

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?

The description names a specific verb and resource ('Evaluate a purchase against the spend policy') and immediately scopes it as a non-submitting dry run, which cleanly separates it from sibling tools like submit_purchase_intent and request_ephemeral_card. An agent can tell what it does and what it does not do without reading the schema.

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?

It establishes the clear context of pre-flight evaluation ('without submitting it') and reinforces that no card is issued and no human is pinged, which tells the agent this is the cheap, safe first step. It stops short of explicitly naming which sibling to call after a given decision, so it lacks a full when-to-use-next narrative.

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