Skip to main content
Glama
FlowState by DialectForge

FlowState by DialectForge

Official

manage_todos

Destructive

Track and coordinate shared to-do items by updating statuses, blocking dependencies, and claiming tasks to prevent conflicting work.

Instructions

Todos. list; next: top unblocked (others' claims last). update: status (done/cancelled), priority, title, description. block / unblock: waits on todos or a problem. add: subtask, blocker or due date only (else log_work). claim before you start (fails if someone has it); renew; release or handoff (with a note). Returns rows.

Input Schema

NameRequiredDescriptionDefault
sortNolist: default priority.
limitNonext: how many (default 5).
modelNoModel name if known. Never guess.
titleNoadd (required) / update.
actionYesThe operation; see the tool description.
statusNoupdate: new. list: filter.
compactNolist: shorter rows.
minutesNoclaim / renew: 1-120, default 15.
projectYesProject name or id. Required.
todo_idNo#id in the brief.
due_dateNoadd: ISO due date.
priorityNoadd / update. list: filter.
next_stepNohandoff: the next step.
blocked_byNoTodo ids it waits on.
descriptionNoadd / update.
where_i_wasNohandoff: your progress.
component_idNoadd: component id.
min_priorityNolist: this or more urgent.
parent_todo_idNoadd: parent todo id.
blocked_by_problemNoProblem id it waits on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.4.3
    • changedInput schema / properties / blocked_by / description
      Previous value: -"Todo ids it waits on (unblock: omit = all)."New value: +"Todo ids it waits on."
    • changedInput schema / properties / model / description
      Previous value: -"Your model name if you know it. Never guess."New value: +"Model name if known. Never guess."
  2. Changed16 schema fields changedv2.3.0
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "list",
      -  "next",
      -  "update",
      -  "block",
      -  "unblock",
      -  "add"
      -]New value: +[
      +  "list",
      +  "next",
      +  "update",
      +  "block",
      +  "unblock",
      +  "add",
      +  "claim",
      +  "renew",
      +  "release",
      +  "handoff"
      +]
    • changedInput schema / properties / blocked_by / description
      Previous value: -"add / block / unblock: todo ids it waits on. unblock without blockers clears all."New value: +"Todo ids it waits on (unblock: omit = all)."
    • changedInput schema / properties / blocked_by_problem / description
      Previous value: -"add / block / unblock: a problem id it waits on."New value: +"Problem id it waits on."
    • changedInput schema / properties / component_id / description
      Previous value: -"add: its component id."New value: +"add: component id."
    • changedInput schema / properties / description / description
      Previous value: -"add / update: longer detail."New value: +"add / update."
    • changedInput schema / properties / limit / description
      Previous value: -"next: how many todos. Default 5."New value: +"next: how many (default 5)."
    • changedInput schema / properties / min_priority / description
      Previous value: -"list: this priority or more urgent."New value: +"list: this or more urgent."
    • addedInput schema / properties / minutes
      Added value: +{
      +  "description": "claim / renew: 1-120, default 15.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / next_step
      Added value: +{
      +  "description": "handoff: the next step.",
      +  "type": "string"
      +}
    • changedInput schema / properties / parent_todo_id / description
      Previous value: -"add: parent todo id (makes it a subtask)."New value: +"add: parent todo id."
    • changedInput schema / properties / priority / description
      Previous value: -"add / update: the priority. list: only this one."New value: +"add / update. list: filter."
    • changedInput schema / properties / sort / description
      Previous value: -"list: sort order. Default priority."New value: +"list: default priority."
    • changedInput schema / properties / status / description
      Previous value: -"update: the new status. list: only this one."New value: +"update: new. list: filter."
    • changedInput schema / properties / title / description
      Previous value: -"add: the title (required). update: a new title."New value: +"add (required) / update."
    • changedInput schema / properties / todo_id / description
      Previous value: -"update / block / unblock: the todo id (#id in the brief)."New value: +"#id in the brief."
    • addedInput schema / properties / where_i_was
      Added value: +{
      +  "description": "handoff: your progress.",
      +  "type": "string"
      +}
  3. Addedv2.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructive, non-idempotent behavior, and the description adds operational context beyond them: claims can fail if someone else has the todo, renew/release/handoff are part of the workflow, and handoff requires a note. It does not explain exactly which actions are destructive or what a destructive update can remove, leaving some important behavioral detail to the annotations.

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 one dense, front-loaded paragraph with no filler; action labels make it scannable despite the telegraphic style. A few fragments are ambiguous and 'Todos.' is close to restating the title, but overall it is appropriately sized for a multi-action tool.

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 tool with 10 actions and 20 parameters, it covers the action set, key workflow constraints, and sibling routing well. The main gap is return behavior: 'Returns rows' is thin without an output schema, and destructive-action details are not expanded, but the schema carries parameter meaning and the description remains sufficient for correct invocation.

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 description coverage is 100%, so the schema already documents the 20 parameters well. The description still adds useful action-specific semantics: add is limited to subtask/blocker/due date, handoff carries a note, claim must happen before work starts, and update covers status/priority/title/description.

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 names the todo resource and enumerates the action set (list, next, update, block/unblock, add, claim/renew/release/handoff) with specific semantics for each. It is not a single crisp purpose statement, but an agent can distinguish this tool's scope from siblings like log_work through the explicit routing note.

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 gives action-level guidance: use next for top unblocked items, add only for subtask/blocker/due date, otherwise use log_work, and claim before starting because claims fail if taken. It does not fully clarify when to use overlapping siblings such as manage_handoffs versus the handoff action, so it falls short of exhaustive 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.