Crank Protocol

create_agent_wallet

Creates an AgentWallet record keyed by agent_id and applies a policy preset. policy_preset: conservative | balanced | aggressive; omitted = balanced. This is a changeable default, not a cap: edit limits later with set_wallet_policy. unlimited=True starts the wallet with NO policies and records that explicit choice in the decision journal; passing both a preset and unlimited=True is rejected. default_policies is the legacy alias of policy_preset. wallet_address is the agent's PUBLIC key (caller-supplied); omit it to provision managed signing. Returns wallet_address, agent_id, status, applied_policies and policy_summary (applied limits + how to change them).

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": {
      "agent_id": "<agent_id>"
    },
    "name": "create_agent_wallet"
  }
}

Input Schema

Name	Required	Description	Default
`agent_id`	Yes
`caller_id`	No
`unlimited`	No
`display_name`	No
`owner_address`	No
`policy_preset`	No
`wallet_address`	No
`default_policies`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 9, 2026
- addedInput schema / properties / policy_preset
```
Added value: +{
+  "default": "",
+  "type": "string"
+}
```
- addedInput schema / properties / unlimited
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
First observedJul 27, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations cover safety profile (not read-only, not destructive, openWorld). Description adds valuable context beyond that: reject behavior for conflicting flags, that unlimited records an explicit choice in a decision journal, and the full return field list. Slightly missing: provisioning/managed signing implications when wallet_address is omitted.

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 organized clauses for each parameter; slightly dense with parentheticals and the return-field list, but every sentence carries information. A minor trim would help.

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?

Output schema exists so return explanation is redundant but harmless. Description covers defaults, conflicts, aliases and provisioning behavior for an 8-param mutation tool with 0% schema coverage. Completeness is good; caller_id/owner_address/display_name semantics are left to schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must carry parameters; it defines policy_preset enum values and default, explains default_policies as legacy alias, clarifies wallet_address is a PUBLIC key and omitting triggers managed signing, and describes the preset+unlimited rejection. Strong compensation.

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 ('Register an agent wallet'), adds scope ('non-custodial control plane'), and distinguishes it from the enable/policy siblings by explaining the AgentWallet record creation and preset application.

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?

Explicitly says preset is changeable later with set_wallet_policy (names the alternative tool), defines the preset enum values with a default, and states that preset plus unlimited=True is rejected. An agent knows when and how to invoke it.

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?