Nutcracker

Start task

start_task

Start a creative task (writing, strategy, naming, ideas, research-backed docs) as a new Nutcracker chat in a space; the space brand memory and pins apply. Returns task_id and the chat url. A task takes minutes: poll get_task until it is no longer running.

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": {
      "brief": "<brief>",
      "space_id": "<space_id>"
    },
    "name": "start_task"
  }
}

Input Schema

Name	Required	Description
`brief`	Yes	What you need, in plain words.
`files`	No	file_id values from sending files to upload_file urls.
`context`	No	Facts, numbers, sources and constraints the work must rest on.
`doc_ids`	No	Docs, presentations or storyboards the task must read (ids from get_task, list_space or create_doc).
`space_id`	Yes	A space id from list_spaces.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the key behavioral traits: a new chat is created inside the space, inherited brand memory and pins take effect, the call returns task_id and chat url, and the work is asynchronous and takes minutes. That async/polling contract is exactly the context an agent cannot get from the structured fields.

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?

Three sentences, front-loaded with purpose, then return value, then the polling imperative. No filler; every clause carries operational information.

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 5-parameter creation tool with no output schema, the description covers what it creates, what it returns, how long it takes, and what to do next. Nothing an agent needs in order to invoke and follow up correctly is missing.

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 description coverage is 100%, so every parameter (brief, files, context, doc_ids, space_id) is already documented in the schema with sourcing hints. The description only indirectly touches space_id via "space brand memory and pins apply" and adds no format or constraint detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb ("Start") and resource ("a creative task ... as a new Nutcracker chat in a space") and enumerates the task domains (writing, strategy, naming, ideas, research-backed docs). An agent can immediately tell this creates a new chat-based task rather than editing an existing doc or space.

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?

The creative-work framing and the note that space brand memory/pins apply give clear context for when this is the right call, and it explicitly instructs polling get_task rather than waiting synchronously. It stops short of naming exclusions (e.g. when to prefer generate or create_doc), so it falls just under a 5.

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

All Nutcracker 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?