Skip to main content
Glama
kimi-sessions
by KekcuHa

Message another Kimi Code session

SendMessage

Send plain text messages between Kimi Code sessions by specifying sender and recipient IDs; queued delivery can steer a running turn immediately.

Instructions

Send plain text to another Kimi Code session. The sender name or ID is required because stdio MCP does not identify the calling session. The message is queued by Kimi; steer=true also lets a running turn consume it immediately. No permissions are transferred.

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": {
      "to": "<to>",
      "from": "<from>",
      "text": "<text>"
    },
    "name": "SendMessage"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesRecipient's exact session name or session_ ID
fromYesSender's exact session name or session_ ID
textYesPlain text message; do not include credentials
steerNoDeliver a queued message to the active turn instead of waiting for the next turn

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.3

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that messages are queued by Kimi, that steer changes delivery timing, that no permissions are transferred, and why the sender is required (stdio does not identify the caller). It omits failure modes such as unknown recipient handling and any rate limits, leaving a modest gap.

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 the action, then the sender requirement, then delivery semantics, then the security note. No filler or repetition.

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?

Complete enough for a four-parameter send tool with no output schema: purpose, required sender rationale, delivery behavior, and permission scope are all covered. Only error/failure behavior on the recipient side is unaddressed.

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 adds genuine meaning by explaining why `from` is mandatory (stdio cannot identify the caller) and clarifying that `steer` controls queued-vs-immediate consumption, which goes beyond the schema's one-line property text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: "Send plain text to another Kimi Code session." An agent can tell what the tool does immediately, though it doesn't explicitly contrast with siblings GetMessages/ListAgents (read-side tools).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: it explains that steer=true lets a running turn consume the message immediately, which hints at the when. It never says when not to use it, nor when to prefer GetMessages/ListAgents or a direct reply.

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

Deploy Server

Other Tools