Skip to main content
Glama

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

Proxy implementation, Base

base_proxy
Read-only

Find the implementation behind a proxy contract on Base: 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=0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913. 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": "base_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 cover the read-only/destructive/open-world profile, and the description adds genuinely new behavioral facts: failed calls are free, malformed address returns 400, codeless address returns 422, and each successful call is billed. It also implicitly explains why idempotentHint=false (repeat calls are charged), which is valuable context the annotations cannot convey. It does not describe the shape of a successful response, so it falls short of a 5.

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?

Purpose is front-loaded, followed by usage guidance, error semantics, an example, and pricing, so the ordering is sensible. There is mild redundancy in stating the charging model twice ('Price $0.01/call via x402' and later 'each call is charged, so repeats are not free'), and the density of clauses makes it a single heavy paragraph, but nearly every sentence carries information.

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?

With no output schema and a single-parameter schema, the description still answers the questions that matter: what it reads, what it reports ('names the kind found'), what failures look like, and what it costs. The main remaining gap is that the success payload (implementation address, admin/beacon values, proxy kind) is only alluded to, not described.

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 meaning beyond it: a concrete example address and the input-validation contract (malformed input yields 400, codeless address yields 422). That helps an agent format and sanity-check the single argument rather than just knowing its type.

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 Base') and enumerates the exact detection techniques (EIP-1967 implementation/beacon/admin slots, EIP-1822 UUPS, legacy OpenZeppelin layout, EIP-1167 minimal-proxy bytecode) plus the output ('names the kind found'). An agent can distinguish this from base_is_contract or base_call without opening any schema.

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 the alternative for a broader need ('for a fuller risk verdict use contract_risk'). The exclusion is grounded in the tool's actual capability rather than left to inference.

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.