Agent Einstein — Crypto & Market Intelligence

Token Safety Check

check_token_safety

Read-onlyIdempotent

Free honeypot / risk screen for an EVM token contract, from the cached GoPlus security dataset. This is the quick screen — the paid analyze_token_security tool runs a live, deeper scan on any contract including ones not in the cache.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`chain`	No	Chain the contract is deployed on.	base
`contract`	Yes	Token contract address, 0x-prefixed 40 hex characters.

Output Schema

TableJSON Schema

Name	Required	Description
`chain`	No	Chain it was screened on.
`flags`	No	Individual risk flags recorded against the contract.
`reason`	No	Why the payload is absent, when `available` is false.
`result`	No	The raw cached row, for fields this summary does not normalize.
`contract`	No	Contract that was screened.
`honeypot`	No	True when the cached scan flagged it as a honeypot.
`screened`	No	FALSE means the contract is not in the cached dataset — "not screened", NOT a clean bill of health. Only a true here makes the other fields meaningful.
`available`	No	False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
`fetchedAt`	No	When the underlying snapshot was refreshed (epoch ms, or ISO-8601 for the Bitcoin cycle feed). Age matters: these are cached reads, not live queries.
`riskLevel`	No	Risk grade recorded by the scan.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "available": {
+      "description": "False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.",
+      "type": "boolean"
+    },
+    "chain": {
+      "description": "Chain it was screened on."
+    },
+    "contract": {
+      "description": "Contract that was screened."
+    },
+    "fetchedAt": {
+      "description": "When the underlying snapshot was refreshed (epoch ms, or ISO-8601 for the Bitcoin cycle feed). Age matters: these are cached reads, not live queries."
+    },
+    "flags": {
+      "description": "Individual risk flags recorded against the contract.",
+      "items": {},
+      "type": "array"
+    },
+    "honeypot": {
+      "description": "True when the cached scan flagged it as a honeypot."
+    },
+    "reason": {
+      "description": "Why the payload is absent, when `available` is false.",
+      "type": "string"
+    },
+    "result": {
+      "additionalProperties": true,
+      "description": "The raw cached row, for fields this summary does not normalize."
+    },
+    "riskLevel": {
+      "description": "Risk grade recorded by the scan."
+    },
+    "screened": {
+      "description": "FALSE means the contract is not in the cached dataset — \"not screened\", NOT a clean bill of health. Only a true here makes the other fields meaningful."
+    }
+  },
+  "type": "object"
+}

AddedAug 17, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful context beyond those annotations: the check is free, quick, and backed by a cached GoPlus dataset rather than a live scan. This clarifies the data-freshness tradeoff without contradicting the annotations.

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?

Two tight sentences deliver the core purpose, data source, and the key comparison to the sibling tool. Every phrase earns its place, and the most decision-relevant information is front-loaded.

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?

For a simple read-only tool with full schema coverage and an output schema, the description covers the intended use, the data source, the limitation relative to the live alternative, and when to choose that alternative. Nothing essential is missing for an agent to call it correctly.

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?

The schema already documents both parameters at 100% coverage, including the chain enum, default, and contract format. The description does not add parameter-specific meaning, so the baseline score of 3 is appropriate; no additional compensation is needed.

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 action ('honeypot / risk screen'), a clear resource ('EVM token contract'), and a specific data source ('cached GoPlus security dataset'). It also explicitly separates itself from analyze_token_security, so an agent can distinguish the two tools at a glance.

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?

The description explicitly states this is the 'quick screen' and contrasts it with the 'paid analyze_token_security tool' that runs a 'live, deeper scan' on contracts 'including ones not in the cache.' This gives an agent clear routing criteria: use this for cached quick checks and the sibling for deeper or non-cached coverage.

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

All Agent Einstein — Crypto & Market Intelligence 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.