Skip to main content
Glama

Take open steps off a task

unplan
Destructive

Take unticked steps off an open task. With to they are handed on, after that task's own steps, instead of dropped. One ticked step among them and nothing changes.

Instructions

Take unticked steps off an open task. With to they are handed on, after that task's own steps, instead of dropped. One ticked step among them and nothing changes.

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": {
      "task": "<task>"
    },
    "name": "unplan"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoId of another open task, not said done, to hand them to
stepNoOne step, by its text
taskYesThe task id
stepsNoThe steps to take off, by their text as `read` shows it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.47.1
    • changedInput schema / properties / steps / description
      Previous value: -"The steps to take off, by their text as `read` shows it; case and accents do not matter"New value: +"The steps to take off, by their text as `read` shows it"
  2. Changed1 schema field changedv1.47.0
    • changedInput schema / properties / to / description
      Previous value: -"Id of another open task you may work on, not said done, to hand them to"New value: +"Id of another open task, not said done, to hand them to"
  3. Changed3 schema fields changedv1.43.2
    • changedInput schema / properties / step / description
      Previous value: -"One step, by its text — the same as `steps` with one entry"New value: +"One step, by its text"
    • changedInput schema / properties / steps / description
      Previous value: -"The steps to take off, each by its text as `read` shows it — capitals, accents and the spaces at either end decide nothing. One of `steps` or `step` has to come with the call"New value: +"The steps to take off, by their text as `read` shows it; case and accents do not matter"
    • changedInput schema / properties / to / description
      Previous value: -"The id of another task you may work on, open and not said done, to add these steps to after its own"New value: +"Id of another open task you may work on, not said done, to hand them to"
  4. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, so the safety profile is carried structurally; the description adds the non-obvious atomicity rule that a single ticked step aborts the whole operation. That is valuable behavior beyond annotations (no partial mutation), though it doesn't state error/response behavior or non-idempotency implications.

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?

Three short sentences, front-loaded with the core action, then the conditional behavior, then the guardrail. No filler, though the fragment 'One ticked step among them and nothing changes' is slightly clipped.

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?

For a 4-parameter destructive mutation with no output schema, the description covers what is removed, where it goes, ordering, and the all-or-nothing precondition. Missing only what a successful/aborted call returns and whether the target task must be open, which are minor.

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 coverage is 100%, so every parameter including `to`, `step`, and `steps` is documented in structured data and baseline is 3. The description adds ordering meaning for `to` ('after that task's own steps') and the ticked-step precondition, which is modest but genuine extra value.

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+resource: taking unticked steps off an open task, with the conditional hand-on behavior made explicit. It is clearly distinct from a planning/adding tool, though it names no sibling by name to route against.

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?

The 'With `to` they are handed on ... instead of dropped' clause tells the agent which mode to pick when it wants to preserve the steps, which is real usage guidance. However, there is no explicit when-to-use vs. when-not framing against alternatives (e.g. reword_step or plan), so it stays implied.

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