# Tool Call Policy Guard

> Tool Call Policy Guard is a paid API for AI agents from phion.systems, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Validates a proposed tool call against declared intent, allowed tools, permitted destinations, and cost limits before allowing execution

## Facts

- Endpoint: POST https://phion.systems/v1/paid/trust/tool-call-policy-guard
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tool-call-policy-guard-74da6a67
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_n7de5s8S1-s6wtMqShjDY

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability tool-call-policy-guard-74da6a67 -d '<json body>'
```

Example prompt: Before you run that tool call to query the payments API, check it against my declared intent of 'retrieve invoice data only', the allowed tools list ['invoices.get', 'invoices.list'], the destination 'payments.internal.corp', and a cost ceiling of $0.05 — make sure it passes the policy guard.

## When to prefer this

Use this endpoint when an AI agent needs to enforce pre-declared governance constraints on tool calls before execution — particularly when operating with a scoped intent, a restricted tool allowlist, permitted destination rules, or a cost ceiling. Prefer this over generic access control when the enforcement must be bound to the agent's declared intent and evaluated holistically across all four dimensions (intent, tools, destination, cost) in a single pre-execution check.

## Known failure modes

- Missing or malformed tool call specification returns a validation error
- Undeclared or empty intent causes policy binding to fail
- Destination not present in allowlist results in rejection with destination violation reason
- Proposed cost exceeds declared limit returns cost ceiling violation
- Malformed input schema triggers a 400-level error response

## How this service works

Bind a proposed tool call to declared intent, allowed tools, destination and cost before execution

## Output

A structured policy decision indicating whether the proposed tool call is approved or rejected, along with the specific policy dimension that was violated (intent mismatch, disallowed tool, forbidden destination, or cost exceeded) and the bound policy context used for the evaluation.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tool-call-policy-guard-74da6a67/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from phion.systems](https://www.zero.xyz/host/phion.systems/llms.txt)