Skip to main content
Glama

block_action

Act on a planned block (blockId from get_schedule): start it now (a future block moves to now), complete it (a running block ends now; taskDone also finishes the whole task), snooze it (the planner finds a slot at least minutes later, default 60), extend it by minutes (default 15; the task's estimate grows too), skip a routine for that day, move it to a new start (it stays fixed there; the block keeps its length), unschedule a task (all its unstarted blocks go and the task waits under "Nicht eingeplant" until it is picked again), or mark a block that is over and was never started as missed (it is removed and the task is planned again). The rest of the plan is replanned right away.

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": {
      "id": "<id>",
      "action": "<action>"
    },
    "name": "block_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe block id
startNomove: the new start, e.g. 2026-10-09T14:00 (your time zone) or with an offset/Z; the block keeps its length and is fixed there
actionYes
minutesNosnooze: wait at least this long (default 60); extend: add this much (default 15, at most 240)
taskDoneNocomplete: the whole task is finished

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only state readOnlyHint=false and destructiveHint=false; the description goes far beyond by disclosing real consequences: unschedule removes all unstarted blocks and parks the task under "Nicht eingeplant", missed deletes the block and replans the task, extend grows the task's estimate, and the rest of the plan is replanned immediately. That side-effect disclosure is exactly what an agent needs before mutating a schedule.

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?

Front-loaded with the core purpose and free of filler, but the entire body is one long run-on sentence with stacked parentheticals. An enumerated list of the eight actions would scan faster for an agent choosing a mode.

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?

Covers every input parameter and the downstream scheduling effects, which is strong for a 5-parameter mutation tool with no output schema. It never says what the call returns (the updated plan?) or whether the blockId becomes invalid after actions like missed or unschedule, leaving a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning well past the 80%-covered schema: it ties minutes to different defaults per action (60 for snooze, 15 for extend) and adds an extend-specific cap of 240 that the schema's 10080 maximum does not express, explains taskDone also finishes the whole task, and clarifies that move keeps block length and pins it. This is genuine semantic enrichment.

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 (act on) and resource (a planned block), then enumerates all eight supported actions with their concrete effects. It also points to get_schedule as the source of blockId, so an agent can tell this apart from schedule-reading and task-editing siblings.

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?

Each action's use case is spelled out (start a future block, complete a running one, snooze, extend, skip a routine, move, unschedule, mark missed), which effectively tells the agent when each mode applies. What's missing is explicit exclusion guidance — nothing says when to prefer replan or update_task instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources