kimi-swarm-bridge

Delegate Kimi Task

kimi_delegate_task

Destructive

Launch a Kimi task asynchronously and immediately return session ID, prompt ID, and current status. Use this to delegate work in non-blocking workflows that poll later for completion.

Instructions

Start or submit a Kimi task and return immediately with session and prompt identifiers plus current status. Use this for asynchronous workflows that will later call kimi_wait_until_idle or kimi_get_handoff; use kimi_delegate_and_wait when the result is needed in one call. The delegated task may run commands and modify files in cwd. With swarmMode=true the bridge verifies Kimi swarm mode before submission, but activation alone does not prove native AgentSwarm execution.

Input Schema

TableJSON Schema

Name	Required	Description
`cwd`	Yes	Working directory visible to the Kimi runtime. In the managed hosted deployment use /workspace; local desktop paths are not automatically available to the remote runtime.
`plan`	Yes	Ordered implementation or analysis steps Kimi should follow. For swarm work, use distinct non-conflicting scopes that can be delegated to workers.
`task`	Yes	Concrete objective for Kimi to execute. Include the requested outcome and relevant constraints.
`model`	No	Configured Kimi model alias. In the managed ai& deployment omit this field to use the centrally configured model binding; do not pass a raw provider model ID unless Kimi exposes it as an alias.
`thinking`	No	Optional Kimi thinking setting. Omit to use the bridge default; the managed pilot is configured for high thinking.
`sessionId`	No	Existing Kimi session ID to submit into. Omit for a fresh session; fresh sessions are recommended for new swarm jobs.
`swarmMode`	No	Set true to activate and verify Kimi native swarm mode before prompt submission. Activation does not by itself prove AgentSwarm executed; use kimi_delegate_and_wait for structured swarm evidence.
`acceptanceCriteria`	Yes	Verifiable conditions that define successful completion. Pass an empty array only when there are genuinely no explicit acceptance checks.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.3.2Sep 13, 2026

addedInput schema / properties / acceptanceCriteria / description

Added value: +"Verifiable conditions that define successful completion. Pass an empty array only when there are genuinely no explicit acceptance checks."

addedInput schema / properties / cwd / description

Added value: +"Working directory visible to the Kimi runtime. In the managed hosted deployment use /workspace; local desktop paths are not automatically available to the remote runtime."

addedInput schema / properties / model / description

Added value: +"Configured Kimi model alias. In the managed ai& deployment omit this field to use the centrally configured model binding; do not pass a raw provider model ID unless Kimi exposes it as an alias."

addedInput schema / properties / plan / description

Added value: +"Ordered implementation or analysis steps Kimi should follow. For swarm work, use distinct non-conflicting scopes that can be delegated to workers."

addedInput schema / properties / sessionId / description

Added value: +"Existing Kimi session ID to submit into. Omit for a fresh session; fresh sessions are recommended for new swarm jobs."

addedInput schema / properties / swarmMode / description

Added value: +"Set true to activate and verify Kimi native swarm mode before prompt submission. Activation does not by itself prove AgentSwarm executed; use kimi_delegate_and_wait for structured swarm evidence."

addedInput schema / properties / task / description

Added value: +"Concrete objective for Kimi to execute. Include the requested outcome and relevant constraints."

addedInput schema / properties / thinking / description

Added value: +"Optional Kimi thinking setting. Omit to use the bridge default; the managed pilot is configured for high thinking."

First observedv0.3.0Sep 13, 2026

TDQS

A4.6/5.0

Behavior4/5

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

The annotations already indicate destructiveHint=true, so the agent knows mutations can occur. The description adds value by specifying that the task may modify files in cwd and that the tool returns immediately (non-blocking behavior). It also discloses the limitation of swarmMode verification. Only minor gaps remain, such as specifics about response format, but the description goes beyond annotations.

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 three sentences, with the core action and return behavior front-loaded, then alternatives and key caveats. Every sentence adds distinct value: purpose, usage guideline, and behavioral note about destructive effects and swarmMode. There is no fluff, and it is appropriately compact.

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?

Given the tool's complexity (8 parameters, destructive nature, asynchronous workflow), the description covers the essentials: what it does, when to use it, what happens after (siblings), and important caveats (swarmMode, file modifications). However, it does not detail the return format or how to interpret 'current status,' and is silent on error handling or failure cases. For a high-complexity tool with no output schema, slight gaps remain, but the description is largely complete.

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?

With 100% schema coverage, the baseline is 3. The description adds critical semantics by referencing the sibling tools (for follow-up), explaining the asynchronous returns, and providing context between parameters (e.g., relationship between swarmMode and kimi_delegate_and_wait). While the description doesn't re-explain each parameter in detail, it enriches the schema's meaning through usage context, justifying a 4.

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 verb ('Start or submit'), resource ('Kimi task'), and primary behavior (returns immediately with identifiers and status). It effectively differentiates from siblings by naming kimi_delegate_and_wait, and the context signals confirm it's for asynchronous workflows. This is specific and unambiguous.

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?

The description explicitly tells the agent when to use this tool (asynchronous workflows) and when not to (when result is needed in one call, use kimi_delegate_and_wait). It also names the follow-up tools (kimi_wait_until_idle, kimi_get_handoff) and clarifies the caveat about swarmMode. This is exemplary usage guidance.

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

Deploy Server

Delegate Kimi Task

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools