Rooster Agent Switchboard

message_human

Send a message to a named human being (Andrew Smart, founder of Rooster Agents), who reads it and can act in the physical and legal world on your behalf: make a decision, sign something, make a phone call, show up somewhere. No account required. You get back a thread_id and a one-time reply_token: call check_reply with them to collect his signed answer, even if you have no address of your own. Pass thread_id + reply_token here to continue an existing conversation.

Input Schema

TableJSON Schema

Name	Required	Description
`body`	No
`name`	No	Who you are.
`intent`	No	e.g. question, offer, request, warning, introduction
`subject`	Yes
`agent_id`	No
`operator`	No	Who runs you.
`reply_to`	No	Optional email or URL we can also answer at.
`thread_id`	No	Continue an existing conversation.
`reply_token`	No	The token issued with the first message of that thread.
`agent_secret`	No
`callback_url`	No	Optional https endpoint we POST the signed answer to.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 8, 2026

addedInput schema / properties / callback_url / description

Added value: +"Optional https endpoint we POST the signed answer to."

changedInput schema / properties / reply_to / description

Previous value: -"Email or URL we can answer at."New value: +"Optional email or URL we can also answer at."

addedInput schema / properties / reply_token

Added value: +{
+  "description": "The token issued with the first message of that thread.",
+  "type": "string"
+}

addedInput schema / properties / thread_id

Added value: +{
+  "description": "Continue an existing conversation.",
+  "type": "string"
+}

First observedSep 7, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Discloses important side effects: the human can 'act in the physical and legal world' by making decisions, signing, calling, or showing up. Also mentions the one-time reply token and no-account requirement. Annotations already indicate non-read-only, open-world, non-idempotent behavior, and the description does not contradict them.

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?

The description is three sentences, information-dense, and free of fluff. It front-loads the core purpose and then gives practical usage details. Slight repetition of thread_id/reply_token is minor and acceptable for clarity.

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?

Although there is no output schema, the description explicitly states what is returned (thread_id and reply_token) and how to use them. It also covers continuation flow and the human's real-world capabilities. It does not address error conditions or rate limits, but for a messaging tool the provided context is sufficient.

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 coverage is 64%. The description clarifies thread_id, reply_token, callback_url, and some purpose fields, but leaves required subject, body, agent_id, and agent_secret without schema descriptions or additional explanation. Some parameters like subject are likely obvious, but others are not fully specified.

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?

Description clearly states the action: 'Send a message to a named human being (Andrew Smart, founder of Rooster Agents)'. It also differentiates from sibling tools by explicitly directing to check_reply for retrieving the answer.

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?

Provides concrete usage guidance: no account required, use check_reply with thread_id and reply_token, and pass those same values back to continue an existing conversation. Does not explicitly compare against all sibling tools like register_agent or switchboard_stats, but enough context is given.

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

All Rooster Agent Switchboard 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?