Skip to main content
Glama

Agent Data Tools: Full list (every tool as its own definition)

Proxy implementation, Polygon

polygon_proxy
Read-only

Find the implementation behind a proxy contract on Polygon PoS: reads the EIP-1967 implementation, beacon and admin slots, EIP-1822 (UUPS), the older OpenZeppelin layout and EIP-1167 minimal-proxy bytecode, and names the kind found. Use before trusting or decoding a contract whose code can be swapped by its admin; for a fuller risk verdict use contract_risk. A malformed address is 400; an address without code is 422, both uncharged. Example: address=0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

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": {
      "address": "<address>"
    },
    "name": "polygon_proxy"
  }
}

Input Schema

NameRequiredDescriptionDefault
addressYes0x contract address

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, but the description adds real context beyond them: it restates that the tool reads or computes only and changes nothing, and it explains the billing model ($0.01/call, first 25 free, failed calls free) which effectively justifies idempotentHint=false — repeats cost money even though the result is identical. The uncharged-error detail rounds out the behavioral picture. Minor gap: no note on caching or latency for repeated lookups of the same address.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and the detection methods, then guidance, then error codes, then a pricing tail. Nearly every clause carries information, but the billing sentence (x402 USDC, card key, /credits) is the longest element and is secondary to selecting or invoking the tool correctly, so it slightly dilutes focus.

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?

No output schema exists, and the description compensates partially by stating it "names the kind found," implying the response includes a classification plus the resolved implementation. For a one-parameter, read-only lookup that is close to complete, though it never says whether the raw slot values or only the resolved address are returned.

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?

With a single parameter at 100% schema coverage, the baseline is 3, and the description genuinely adds validation semantics the schema lacks — that a malformed address yields 400 and a codeless address yields 422 — plus a concrete well-formed example address. It does not, however, say whether checksummed/lowercase or non-0x forms are accepted differently.

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?

States a specific verb and resource ("Find the implementation behind a proxy contract on Polygon PoS") and enumerates exactly what it reads: EIP-1967 implementation/beacon/admin slots, EIP-1822 UUPS, older OpenZeppelin layout, EIP-1167 minimal-proxy bytecode, plus the resolved kind. The chain-scoped name is reinforced in prose, so it is clearly distinguishable from the eth_proxy/arb_proxy family and from read siblings like polygon_storage or polygon_is_contract.

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?

Gives an explicit when-to-use condition ("before trusting or decoding a contract whose code can be swapped by its admin") and names an alternative for a different need ("for a fuller risk verdict use contract_risk"). It also documents failure semantics — 400 for malformed address, 422 for an address without code — so an agent knows the boundary conditions before calling.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.