Agent Einstein — Crypto & Market Intelligence

Contract Review · Transaction Debugger · Fund-Flow Trace

inspect_onchain

Read-onlyIdempotent

Block-explorer intelligence on 18 EVM chains, from live Etherscan V2 data. contract reviews a deployed contract — resolving proxies FIRST (EIP-1967, the legacy OpenZeppelin slot USDC still uses, EIP-1167 clones, Gnosis Safe, EIP-2535 diamonds) so the answer describes the implementation that actually executes rather than the delegating stub. transaction explains what one transaction did: decoded method and logs, exact integer gas arithmetic including the L1 data fee on OP-stack chains, asset and permission changes, and decoded revert reasons. flow follows the money from a transaction or wallet across hops and returns a nodes-and-edges graph where every edge carries a real transaction hash. Read-only; nothing is signed or broadcast. [Paid: $0.25–$0.35 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	No	contract = review a deployed contract (needs `address`) · transaction = explain one transaction (needs `txHash`) · flow = trace fund flow from a transaction or wallet.	contract
`chain`	No	Blockchain network.	base
`txHash`	No	Transaction hash (0x + 64 hex).
`address`	No	Contract or wallet address (0x + 40 hex).

Output Schema

TableJSON Schema

Name	Required	Description
`skill`	No	Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.
`reason`	No	Why there is no analysis, when `available` is false.
`analysis`	No	The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
`available`	No	True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the market.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "analysis": {
+      "description": "The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.",
+      "type": "string"
+    },
+    "available": {
+      "description": "True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the market.",
+      "type": "boolean"
+    },
+    "reason": {
+      "description": "Why there is no analysis, when `available` is false.",
+      "type": "string"
+    },
+    "skill": {
+      "description": "Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedSep 4, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already provide the read-only and non-destructive profile, and the description adds substantial behavioral context: proxy resolution order, implementation-vs-stub behavior, exact gas arithmetic including OP-stack L1 fees, and graph edges carrying real transaction hashes. The claim of '18 EVM chains' conflicts with the schema's seven enum values and includes Solana, which is not EVM, so the behavioral disclosure is slightly overconfident.

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 description is dense but organized: a one-line overview, then mode-by-mode behavioral details, then safety and cost/alternatives in a compact final sentence. Every sentence earns its place, and backticked mode names make the structure scannable for an agent.

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?

The description covers invocation modes, required inputs, output characteristics, read-only safety, pricing, and where to find alternatives, and an output schema exists to document return shapes. However, the inconsistency between '18 EVM chains' and the schema's seven-value enum (which includes non-EVM Solana) leaves a real completeness gap that could confuse an agent about supported networks.

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%, so the baseline is 3, but the description adds meaningful parameter-level semantics by explaining what each `kind` produces and what inputs are needed. It clarifies the `flow` mode's graph output and the `transaction` mode's decoded-method and revert-reason details, which go beyond the schema's brief field descriptions.

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 clearly states a specific verb and resource: 'Block-explorer intelligence on 18 EVM chains' with three concrete modes — `contract` reviews, `transaction` explains, and `flow` follows money. This strongly differentiates it from the sibling analytics tools and leaves no doubt about the tool's core function.

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?

Each mode names the input it requires (`contract` needs `address`, `transaction` needs `txHash`, `flow` starts from a transaction or wallet), giving the agent clear selection criteria. It also explicitly points to `list_einstein_capabilities` for free alternatives, which is useful cost-aware guidance, though it does not name specific sibling tools that should be preferred.

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.