Skip to main content
Glama

Ask Kimi (new session) [experimental]

kimi_ask

Ask Kimi K2 questions or give coding instructions in a new session; set a workspace path to provide repo context for the sub-agent.

Instructions

Best for the Kimi K2 family (Moonshot's Kimi Code, kimi -p), in a NEW session. EXPERIMENTAL: built without a Kimi account, so no authenticated round-trip has run; it needs kimi login or an API key in ~/.kimi-code/config.toml (check kimi_status). Pass workspace=; without it the sub-agent sees no repo. Follow up with kimi_continue. NO sandbox: it auto-executes every tool call, so trusted prompts only.

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": {
      "prompt": "<prompt>"
    },
    "name": "kimi_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoOptional model alias (`-m`, from ~/.kimi-code/config.toml); omit to use config's default_model. Not validated up front (Kimi has no `models` list), so a bad alias surfaces as Kimi's own run-time error.
promptYesQuestion or instruction for Kimi.
timeout_sNoMax seconds to wait for kimi to complete. Default 180.
workspaceNoWorking root (kimi's cwd). Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.26.0

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations it discloses the critical behavioral facts: no sandbox, every tool call auto-executes, auth requires `kimi login` or an API key in ~/.kimi-code/config.toml, and the tool is experimental with no authenticated round-trip validated. These are exactly the risk and prerequisite details an agent needs before invoking a mutating, open-world tool and they are consistent with readOnlyHint=false.

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 purpose and the session-scope distinction are front-loaded, and each remaining sentence carries a distinct prerequisite or warning (experimental status, auth, workspace, follow-up, sandbox). It is dense but every clause earns its place; the auth/experimental note is a touch tangled grammatically.

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 an open-world, non-read-only tool with four fully documented parameters and an output schema, the description covers the gaps structured fields cannot: auth prerequisites, absence of sandboxing, workspace consequences, and the follow-up path. Nothing needed to call it correctly or safely 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: workspace=<project dir> and a concrete consequence of omitting it ('the sub-agent sees no repo'), which sharpens the schema's vague 'Defaults to the server cwd'. Model and timeout parameters are left to the schema, which already explains them well.

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?

The description states a specific action and scope: asking the Kimi K2 / Kimi Code CLI in a NEW session, and explicitly contrasts that with following up via kimi_continue. It is slightly indirect by opening with a superlative ('Best for the Kimi K2 family') rather than a plain verb statement, but an agent can still identify the resource and the new-session semantics unambiguously.

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 names the follow-up alternative (kimi_continue) and the auth-check sibling (kimi_status), and gives a real exclusion: 'trusted prompts only' because there is no sandbox. It stops short of a full when-to-use versus other agent tools (claude_ask, codex_ask, etc.), but the intra-family routing is clear.

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