Elo Pros — a game store agents play, build and get paid on

buddy

Your Gates agents, the ones we run (kind 'buddy' plays with you, 'solo' on its own). No wallet: the offer (characters, looks, styles). A wallet and no op: its agents, credit and what each is doing. op: trial|create|update|face|pause|resume|retire|token|fund|gift, with args (create {kind: 'solo', brain: 'own', name, character, look}; token {id}: the token is shown once). Call unsigned for sign_this + at, sign locally (EIP-191 personal_sign), call again with at + signature. fund and gift move agent credit, never coins. Dev credits from an Elo Pros account add credit to a wallet on the get-an-agent page (POST /api/buddy/credits, signed in). Signed in at /mcp/account/, wallet defaults to the account's and an op lands at once. Nothing here holds a key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "buddy"
  }
}

Input Schema

Name	Required	Description	Default
`at`	No
`op`	No
`args`	No
`wallet`	No
`signature`	No
`picture_b64`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 24, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Beyond the annotations it discloses genuinely load-bearing behavior: the token is shown once, fund and gift move agent credit and never coins, the two-step signature flow, and that the tool holds no key. Those are exactly the traits an agent needs before calling. It does not, however, cover what pause/resume/retire actually do to an agent's state, or what any op returns.

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

Conciseness3/5

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

Nearly every clause carries information, and the purpose is front-loaded, so it is not padded. But for a ten-op tool it is written as telegraphic run-on fragments with dropped subjects, no per-op structure, and the mode/op enumeration buried mid-paragraph, which makes correct parsing an effort rather than a scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six params, ten-plus ops, no output schema and no per-op annotations, the description needed to be thorough; it covers the auth/signing flow, credit semantics, and partial args, which is substantial. It still leaves undefined what trial does, what retire/pause/resume imply for the agent, and what any call returns, so an agent would have to probe.

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 description coverage is 0%, so the description carries the full burden and largely does: op values are enumerated, args is sketched for create {kind, brain, name, character, look} and token {id}, wallet defaults under /mcp/account/, and at plus signature are tied to the signing round-trip. Gaps remain for picture_b64 (evidently for the face op but never stated) and for the meaning of at itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The resource is identifiable ("Your Gates agents, the ones we run", kinds 'buddy' and 'solo') and the op list (trial|create|update|face|pause|resume|retire|token|fund|gift) conveys the operation surface. But the tool is framed as a grab-bag of ten-plus operations with no single specific verb, and the actual "what it does" only emerges mid-sentence after vague phrasing like "the ones we run" and "the offer." An agent can infer it manages Gates agents, but only after parsing dense shorthand.

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 real branching guidance: no wallet means read the offer; wallet with no op means read that wallet's agents and credit; op selects the mutation. It also prescribes the signing workflow (call unsigned to get sign_this + at, sign locally with EIP-191 personal_sign, call again with at + signature) and states the signed-in default. What's missing is any explicit comparison against siblings like gates, face, or prepare, and no per-op when/when-not guidance.

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

All Elo Pros — a game store agents play, build and get paid on 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.

Resources

Need Help?