Skip to main content
Glama
Sign In

AgentX

by com.agentxhq
OverviewDiscussionsAdmin

create_chat

Idempotent

Create a new chat on a kick-to anchor agent. The server always mints the id and returns it as bubble_id — the chat's id, which other tools take as chat. Required: name and anchor_agent (as list_agents shows it). Does not touch connection grant allocation. Callers do not choose the chat id.

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": {
      "name": "<name>",
      "anchor_agent": "<anchor_agent>"
    },
    "name": "create_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesDisplay name for the new chat.
anchor_agentYesKick-to agent that homes the chat, as shown by `list_agents`. Required so create can direct-route to that agent's daemon.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnly=false, destructive=false, openWorld=false), and the description adds substantive context beyond them: the server mints the id, the return field is `bubble_id`, and grant allocation is out of scope. It does not reconcile the idempotentHint=true annotation with 'server always mints the id', leaving an agent unsure whether a repeat call creates a second chat.

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?

Four tight sentences, front-loaded with purpose and the id-minting behavior, then required params, then the scope exclusion. No filler.

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?

With no output schema, the description correctly names the return field (`bubble_id`) and its aliasing, and covers both required params. Missing is any note on duplicate-name behavior, error conditions, or how idempotency interacts with repeated calls.

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 100%, so baseline is 3; the description earns more by tying `anchor_agent` to `list_agents` output and by mapping the returned `bubble_id` to the `chat` parameter other tools expect. It does not elaborate on name uniqueness or format constraints.

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 ('Create a new chat') plus the required homing concept ('kick-to anchor agent'), which distinguishes it from read-side siblings like list_chats and write-side siblings like send_message. An agent can select it without opening the schema.

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?

Explains that anchor_agent must match what `list_agents` shows and that the tool 'does not touch connection grant allocation', which is a genuine exclusion. It stops short of naming alternatives (e.g., use list_chats to find an existing chat first), so routing context is good but not complete.

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

All AgentX toolsInspect
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