Tirith

Official

Overview Schema Source Related Servers Discussions Admin

message_send

Send a short coordination message to one agent, all agents active in the last hour, or the human queue. The message is delivered once via inbox on the recipient's next tool call.

Instructions

Send a short message to one agent by name, to every agent active in the last hour with *, or to the human queue with human. It is delivered once, as inbox on the recipient's next call of any tool, and reply_to threads an answer. Use for coordination talk; not for lasting knowledge (memory_write, decision_record) or for code changes others must react to (notice_publish). Messages are dropped after 24 hours.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	The recipient's agent name, `*` for every agent active in the last hour, or `human` for the human queue.
`text`	Yes	The message, at most 1000 characters.
`agent`	Yes	Your stable agent name.
`paths`	No	Paths the message is about.
`reply_to`	No	Id, or a unique prefix, of the message this one answers.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes	ok. not_found: an unknown reply_to. invalid: empty or over-long text, a bad recipient, or agent human.
`message`	No	On ok, the message as sent: id, from, to, text, reply_to, paths, at; audience lists the recipients of a broadcast. On any other outcome, why, as text.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv1.1.2Sep 18, 2026

addedInput schema / properties / agent / description
```
Added value: +"Your stable agent name."
```
addedInput schema / properties / paths / description
```
Added value: +"Paths the message is about."
```

addedInput schema / properties / reply_to / description

Added value: +"Id, or a unique prefix, of the message this one answers."

addedInput schema / properties / text / description

Added value: +"The message, at most 1000 characters."

addedInput schema / properties / to / description

Added value: +"The recipient's agent name, `*` for every agent active in the last\nhour, or `human` for the human queue."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Any result may also carry lost, inbox, inbox_more and persist_error; see guide.",
+  "properties": {
+    "message": {
+      "description": "On ok, the message as sent: id, from, to, text, reply_to, paths, at; audience lists the recipients of a broadcast. On any other outcome, why, as text.",
+      "type": [
+        "object",
+        "string"
+      ]
+    },
+    "status": {
+      "description": "ok. not_found: an unknown reply_to. invalid: empty or over-long text, a bad recipient, or agent human.",
+      "enum": [
+        "ok",
+        "conflict",
+        "not_found",
+        "none",
+        "invalid",
+        "cancelled"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

First observedv1.1.1Sep 18, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The description discloses key behavioral traits beyond the annotations: messages are delivered only once, appear as inbox on the recipient's next tool call, support reply_to threading, and are dropped after 24 hours. This goes well beyond the sparse destructiveHint annotation and gives an accurate model of side effects.

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 compact and well-structured: first the core send action and recipient types, then delivery semantics, then explicit usage boundaries, then retention. Every sentence adds necessary information without repetition or filler.

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 tool with 5 parameters and an output schema, the description covers the important behavioral context: who can receive, how delivery works, how replies thread, when to use it, and what it is not for. The remaining parameter details are already fully documented in the schema, so nothing critical is missing.

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?

The input schema already covers all parameters with descriptions, so the baseline is 3. The tool description adds extra meaning by explaining the special recipient values ('*', 'human'), the threading behavior of reply_to, and the overall 'short message' intent, which clarifies how parameters should be used.

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 clearly states the tool's function: sending a short message to one agent, all active agents, or the human queue. It differentiates from siblings by explicitly naming alternatives like memory_write, decision_record, and notice_publish, and by describing the delivery mechanism.

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?

It explicitly says 'Use for coordination talk; not for lasting knowledge (memory_write, decision_record) or for code changes others must react to (notice_publish).' This gives an agent clear when-to-use and when-not-to-use guidance, naming the exact sibling tools to use instead.

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