Skip to main content
Glama

split_question

Breaks an open question that contains multiple decisions into one question per decision, preserving order and relabeling the parts (Q3.1, Q3.2) while returning those left open.

Instructions

Split an open question that poses several decisions into one question per decision, in its place and order, in one write. Each part is text or { text, implementation?, answer? }: parts inherit the question's (implementation) marker unless they set their own, and a part with an answer is settled as it is written — recorded in record_in (default "Decisions"), or kept ticked with mode "tick", as resolve_question does. Parts are labelled under the question's label (Q3 → Q3.1, Q3.2), and Q3 stops existing. Returns the parts left open with their labels.

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": {
      "ref": "<ref>",
      "into": "<into>"
    },
    "name": "split_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe question's label, e.g. "Q3" (as `get`, `questions` and `next_question` report it).
refYesInitiative (ticket/issue): "collection#n" (e.g. "lgm#22"), a bare number, or a path.
intoYesThe separate questions, in order (at least two).
modeNo
matchNo
record_inNo
collectionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.0.0
    • addedInput schema / properties / id
      Added value: +{
      +  "description": "The question's label, e.g. \"Q3\" (as `get`, `questions` and `next_question` report it).",
      +  "type": "string"
      +}
    • removedInput schema / properties / index
      Removed value: -{
      -  "maximum": 9007199254740991,
      -  "minimum": -9007199254740991,
      -  "type": "integer"
      -}
  2. Addedv2.6.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does so well: it discloses that this is a write operation, that the original question stops existing, that parts inherit the implementation marker, that answered parts are settled immediately, and that the tool returns the parts left open. These are meaningful side-effect and inheritance details beyond the schema. It does not cover failure modes or permissions, but it is substantially transparent for a mutation tool.

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 description is front-loaded with the core operation and then adds necessary details about part structure, inheritance, settlement, labeling, and return value. It is dense and readable as a single paragraph, and the length is justified by the operation's complexity. Some clauses are packed tightly, but there is little obvious waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core split behavior, replacement of the original question, part labeling, answer settlement, and what is returned, which is important because no output schema exists. However, with 7 parameters and only 43% schema description coverage, the unexplained `match` and `collection` parameters leave gaps for correct invocation. It is adequate for the main path but not complete for the full tool surface.

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 only 43%, so the description needs to compensate. It adds useful meaning for `into`, `implementation`, `answer`, `record_in`, and the `mode: "tick"` behavior, but it leaves `match`, `collection`, and the `mode: "remove"` semantics unexplained. The added detail is valuable but does not fully compensate for the low schema coverage.

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 states a specific verb and resource: splitting an open question that contains several decisions into one question per decision, in place and order. It also explains that the original question is replaced, which clearly distinguishes this from simple question creation or resolution. An agent can understand the core operation without opening the schema.

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 description makes the use case clear: an open question posing several decisions should be split into one question per decision. It also notes that parts with an answer behave like resolve_question, which helps with mode selection. It does not explicitly state when not to use this tool or name alternative approaches such as add_question, so it falls short of full when/when-not guidance.

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