Crank Protocol

set_ooda_consent

Idempotent

Opt in/out of the wake-on-condition worker.

Default OFF. When opted in, a triggered alert may run a metered background check (a fast triage model, escalating to a larger model only if worth a closer look) and propose one action. daily_wake_budget (default 10, 1-500) hard-caps metered wakes per day. The worker never executes -- every proposal is approved in your own wallet. See get_ooda_status for wake history including skipped wakes.

Usage-vs-fee-revenue kill threshold: wakes auto-suspend if inference spend over kill_window_days (default 30 days) exceeds kill_threshold_ratio (default "0.5") of attributed fee revenue. kill_threshold_enabled lets you disable the check for this wallet; kill_threshold_ratio is a decimal string. All three are optional -- omit to leave the existing/default value untouched. See get_ooda_status for whether/why a wallet was auto-killed (kill_switched_at, kill_reason).

Workflow: consent step -- run once (or to change budget/kill config) before wakes can fire; check get_ooda_status afterward to confirm state.

Permission mode: a configuration write -- allowed in every permission_mode, observe included; the ladder gates value-bearing actions, not config.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`opted_in`	Yes
`caller_id`	No
`wallet_address`	Yes
`kill_window_days`	No
`daily_wake_budget`	No
`kill_threshold_ratio`	No
`kill_threshold_enabled`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 5, 2026

addedInput schema / properties / kill_threshold_enabled

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedInput schema / properties / kill_threshold_ratio

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedInput schema / properties / kill_window_days

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

AddedJul 27, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations cover write/idempotent/open-world/safe traits, but the description adds substantial non-obvious behavior: default OFF, metered triage-then-escalation wakes, a hard daily cap, guaranteed non-execution of proposals, and auto-suspend kill logic with its trigger conditions. That is materially more than the annotations provide.

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?

Well front-loaded (purpose, then the wait/permission context) and organized into scannable paragraphs, but it is dense and repeats the get_ooda_status pointer twice. Every sentence is informative, though trimming the second status reference would tighten it.

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 config-writing tool with an output schema already covering return values, this description supplies the missing config semantics, the workflow slot, and the permission implications. An agent has everything needed to call it correctly and to know what to do next.

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 0%, so the description carries the load and largely delivers: it documents defaults and ranges for daily_wake_budget (default 10, 1-500), kill_window_days (default 30), kill_threshold_ratio (decimal string default '0.5'), and kill_threshold_enabled, plus the omit-to-preserve semantics. caller_id and the wallet_address role remain unexplained, so it is strong but not complete.

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: opt in/out of the wake-on-condition worker, plus tuning budget and kill config. It is immediately distinguishable from get_ooda_status, which it explicitly names as the read-side sibling.

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 explicit when-to-use ('consent step -- run once (or to change budget/kill config) before wakes can fire') and names the follow-up alternative ('check get_ooda_status afterward to confirm state'). Also clarifies the call is allowed in every permission_mode, including observe.

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?