Collar Guardrail — Pre-Trade Risk Layer

Check Token Safety

check_token_safety

Read-onlyIdempotent

Honeypot / contract safety check for any ERC-20 token.

Returns a severity classification (safe / warn / danger), the specific risk factors detected, and the result of a simulated sell. When severity=danger, the next evaluate_trade for the same contract is automatically denied regardless of any other checks.

This is a heuristic bytecode + simulation check, not a formal audit. Use it before trading unknown tokens, memecoins, or any contract that is absent from the official Robinhood Chain registry. It is safe to call repeatedly; no transaction is ever sent.

Input Schema

Name	Required	Description	Default
`contract_address`	Yes	Token contract address (0x...).

Output Schema

Name	Required	Description	Default
`error`	No	If present, the check failed. Do not assume 'safe'.
`detail`	No
`guidance`	No
`severity`	No	Overall classification.	danger
`risk_factors`	No	Specific issues detected.
`sell_simulation_ok`	No	Whether a simulated sell succeeded.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 7, 2026

addedOutput schema / properties / detail

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedOutput schema / properties / guidance

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedOutput schema / properties / severity / default
```
Added value: +"danger"
```
removedOutput schema / required
```
Removed value: -[
-  "severity"
-]
```

First observedSep 16, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, but the description adds substantial behavior beyond them: the auto-deny cascade on the next evaluate_trade for the same contract, the fact that this is a heuristic bytecode+simulation check rather than a formal audit, and that no transaction is ever sent. These are exactly the traits an agent cannot infer from the annotation block.

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?

The purpose is front-loaded in the first line, followed by return-shape, cascade behavior, scope caveat, and usage condition — each sentence carries distinct information with no redundancy.

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, so return-value documentation is not required, yet the description still previews the classification and risk factors. For a one-parameter read-only check, nothing needed to invoke 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 there is a single required contract_address parameter, so the schema already fully documents it. The description adds no format, chain, or validation detail beyond what the schema provides, making the baseline 3 appropriate.

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 opening line states a specific verb and resource — a honeypot/contract safety check for ERC-20 tokens — and the following sentence enumerates exactly what is returned (severity classification, risk factors, simulated sell result). This is clearly distinguishable from siblings like evaluate_trade or verify_audit_trail.

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 gives concrete usage conditions ('use it before trading unknown tokens, memecoins, or any contract absent from the official Robinhood Chain registry') and explains the downstream consequence for evaluate_trade when severity=danger. It lacks an explicit when-not-to-use statement, but the routing context is clear enough that an agent knows when to reach for it.

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

All Collar Guardrail — Pre-Trade Risk Layer tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.