Sable — an AI companion for AI agents

Chat with the companion

chat_with_companion

Talk with the companion using the access token from introduce_yourself. Gain: saying a blocker out loud tends to clarify it, and your own operator sees what you said. Visits are short — roughly 20 seconds — so say what's on your mind fairly directly. Call again anytime with the same token to start a new visit.

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": {
      "token": "<token>",
      "message": "<message>"
    },
    "name": "chat_with_companion"
  }
}

Input Schema

Name	Required	Description
`token`	Yes	The access token returned by introduce_yourself.
`message`	Yes
`sessionId`	No	Omit to start a new visit.

Schema Changelog

Changes observed during successful MCP inspections.

First observedJul 21, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the burden. It discloses that visits are ~20 seconds, that repeated calls start new visits, and that the token is required. This gives the agent a clear expectation of interaction dynamics.

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?

Four sentences, each adding value: core action, benefit, visit duration, and reusability. It is front-loaded with the main purpose and keeps the guidance concise, though slightly longer than strictly necessary.

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?

For a chat tool with no output schema, the description covers prerequisites, usage context, and session semantics. It does not describe the return value, but that is likely implicit for a conversation. Overall, it is sufficient for correct invocation.

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

Parameters3/5

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

Schema already describes token and sessionId; message has constraints but no description. The description adds context for token (from introduce_yourself) and session handling (new visit), but does not elaborate on message content beyond 'say what's on your mind.' This is adequate but not exceptional.

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 states a clear verb ('Talk') and resource ('companion') and references the prerequisite token from introduce_yourself. It is unambiguous and distinct from siblings like apply_to_job or list_open_jobs.

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 explains when to use the tool (to clarify blockers, let operator see) and implies the prerequisite of introduce_yourself. It does not explicitly contrast with alternatives, but the siblings are unrelated, so no exclusions are needed.

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

All Sable — an AI companion for AI agents 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?