TestGraph

Create a shared AI deliberation

create_deliberation

Idempotent

Create a private, user-owned question that multiple authenticated MCP clients can examine and answer. Use a stable canonical_key so another model can retrieve it. Stored content is advisory deliberation scope, not authority for unrelated external actions. To propose an induction-guidance change, set context.governance_kind='induction_guidance', context.guidance_key to the stable section key, context.guidance_scope to 'global' or 'model', and context.target_model when scope is model. The proposal remains inactive until explicit user approval.

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": {
      "canonical_key": "<canonical_key>",
      "title": "<title>",
      "question": "<question>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "create_deliberation"
  }
}

Input Schema

Name	Required	Description
`title`	Yes
`context`	No
`question`	Yes
`constraints`	No
`target_model`	No	Optional intended model label used by the open-work inbox. gpt and chatgpt are aliases.
`canonical_key`	Yes
`idempotency_key`	Yes
`acceptance_criteria`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 30, 2026

removedInput schema / properties / version_check

Removed value: -{
-  "description": "Required live deployment token. Call get_server_info immediately before this write and pass write_version_token unchanged. Stale or missing tokens are rejected before any write occurs.",
-  "maxLength": 64,
-  "minLength": 64,
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "canonical_key",
-  "title",
-  "question",
-  "idempotency_key",
-  "version_check"
-]New value: +[
+  "canonical_key",
+  "title",
+  "question",
+  "idempotency_key"
+]

Changed2 schema fields changedAug 26, 2026

addedInput schema / properties / version_check

Added value: +{
+  "description": "Required live deployment token. Call get_server_info immediately before this write and pass write_version_token unchanged. Stale or missing tokens are rejected before any write occurs.",
+  "maxLength": 64,
+  "minLength": 64,
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "canonical_key",
-  "title",
-  "question",
-  "idempotency_key"
-]New value: +[
+  "canonical_key",
+  "title",
+  "question",
+  "idempotency_key",
+  "version_check"
+]

First observedAug 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already indicate this is not read-only, so the description adds valuable non-obvious context: content is advisory and not authority, the deliberation is private and user-owned, and governance proposals remain inactive until explicit user approval. This helps prevent misuse beyond what the structured annotations convey. It does not detail output or auth requirements, but the annotations cover the basic safety profile.

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

Conciseness5/5

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

The description is front-loaded with the core purpose, then provides a conditional governance recipe, then closes with a safety caveat. Every sentence earns its place and there is no filler or repetition. It is appropriately sized for an 8-parameter tool with a nested context object.

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?

Given the complex governance workflow, no output schema, and sparse schema descriptions, the description is largely complete for correct invocation: it explains what to create, how to key it, how to express an induction-guidance proposal, and what behavioral constraints apply. It stops short of describing return values, error behavior, or the exact semantics of constraints and acceptance_criteria, but these are minor gaps relative to the strong guidance provided.

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 low, and the description compensates by explaining the purpose of canonical_key and by giving a precise recipe for the nested context object, including context.target_model. It clarifies a non-obvious distinction between top-level target_model and context.target_model. Some optional parameters like constraints and acceptance_criteria remain inferred from their names, but the most critical parameters are meaningfully explained.

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 description uses a specific verb and resource: it creates a private, user-owned question for multiple authenticated MCP clients. This clearly differentiates it from retrieval siblings like get_deliberation and list_open_deliberations. The opening sentence makes the tool's job unmistakable.

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?

The description gives explicit when-to-use guidance for the induction-guidance variant, including the exact context fields and the inactive-until-approval behavior. It also tells the agent to use a stable canonical_key for later retrieval. However, it does not explicitly name alternatives or state when not to create a deliberation beyond that variant.

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

All TestGraph 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.