Crank Protocol

register_counterparty_set

Idempotent

Register/replace/clear the AGNTA counterparty allow-set for the caller's opted-in DelegationGrant (non-custodial control plane).

Persists to Django so the set survives an MCP process restart and is visible to every process -- the durable successor to the earlier process-local InMemoryCounterpartySetResolver. wallet_address must belong to an AgentWallet with a non-blank agnta_grant_pda already configured (opting in is a separate step, out of scope here); the target grant_pda is always resolved from that wallet, never caller-supplied. members is a list of base58 32-byte destination pubkeys the grant's counterparty_root should allow -- pass an EMPTY list to CLEAR the registered set, after which every transfer-class call naming an on-chain destination for this grant fails closed.

expected_root (hex, optional but STRONGLY recommended): compare against the grant's live on-chain counterparty_root (hex-encoded) before calling this -- when given, a set that does not commit to it is refused (INVALID_PARAMS) rather than silently registered, which would otherwise surface later as a confusing AGNTA_GRANT_COUNTERPARTY_DENIED on an unrelated transfer.

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": {
      "wallet_address": "<wallet_address>",
      "members": "<members>"
    },
    "name": "register_counterparty_set"
  }
}

Input Schema

Name	Required	Description	Default
`members`	Yes
`caller_id`	No
`expected_root`	No
`wallet_address`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedAug 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (which only cover safety/idempotency hints), the description discloses durable Django persistence surviving process restart, cross-process visibility, the -derivation rule for grant_pda, fail-closed behavior after clearing, and the concrete failure mode (INVALID_PARAMS for a mismatched expected_root, versus a confusing later AGNTA_GRANT_COUNTERPARTY_DENIED). This is exactly the extra context annotations cannot carry.

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 core action, then preconditions, then the opt-in warning about expected_root. It is dense but every sentence adds operational information; only the aside contrasting with InMemoryCounterpartySetResolver is mildly dispensable.

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 mutating, open-world tool with no schema descriptions and no parameter documentation in the schema, the description supplies preconditions, target derivation, failure semantics, and the durability model. An output schema exists, so return values need not be 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 description coverage is 0%, so the description carries the burden, and it defines members (base58 32-byte destination pubkeys, empty clears), wallet_address (must belong to an AgentWallet with a non-blank agnta_grant_pda), and expected_root (hex, optional, comparison semantics and refusal behavior). caller_id is left entirely undocumented, which keeps it from a 5.

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 first sentence gives a precise verb set (register/replace/clear) plus the resource (AGNTA counterparty allow-set for the caller's DelegationGrant) and even a scope qualifier (non-custodial control plane). It is clearly distinguishable from config-mutation siblings like set_agnta_grant and clear_agnta_grant.

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 states clear context: opting in is a separate, out-of-scope step, and passing an empty members list is the clearing path, with expected_root 'strongly recommended'. However, it never names the alternative tools (set_agnta_grant / clear_agnta_grant / request_agnta_grant_clear) an agent might confuse this with, so routing is inferred rather than explicit.

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

All Crank Protocol 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?