Skip to main content
Glama
lightning-llc-jpn

mustdo-mcp

Official
by lightning-llc-jpn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

TODO を更新

update_todo

Modify a to-do's title, due time, repeat rule, notes, alarm sound, or status by passing only the fields to change, so you can reschedule, reword, or silence existing tasks.

Instructions

TODO の題名・時刻・繰り返し・メモ・音・状態を変える。渡した項目だけ変わる。repeat は丸ごと置き換え（省略した項目は既定値）。repeat: null か {kind: none} で繰り返しを外す。notes: null でメモを消す。繰り返し TODO の status は変えられない（complete_todo / snooze_todo を使う）。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
dueNo鳴らす時刻。YYYY-MM-DDTHH:mm（Account の timeZone の時計）か、オフセット付き ISO8601。YYYY-MM-DD だけなら「その日の既定時刻（Account.defaultTime、既定 09:00）」。
notesNo
soundNoアラーム音。default, chime, marimba, beep, urgent, vibrateOnly, siren, klaxon, rapid, redalert, musicbox, harp, morning, bowl, droplet, breeze, horror, dread, ghost, lament, cello, rainy, fanfare, skip, sparkle
titleNo
repeatNo繰り返し（iOS カレンダーと同じ語彙）。省略した項目は既定値（interval 1・weekdays []・monthly.mode dayOfMonth・end.kind never）。範囲外は INVALID_ARGUMENT。例: 毎日 {kind:daily} / 毎週 月水 {kind:weekly, weekdays:[2,4]} / 隔週 {kind:weekly, interval:2} / 3 日ごと {kind:daily, interval:3} / 毎月 5 日 {kind:monthly}（due を 5 日に）/ 毎月 第 1 月曜 {kind:monthly, monthly:{mode:weekdayOrdinal, ordinal:1, weekday:2}} / 毎月 最終金曜 {kind:monthly, monthly:{mode:weekdayOrdinal, ordinal:-1, weekday:6}} / 毎年 {kind:yearly}（due の月日）/ 10 回で終了 {kind:daily, end:{kind:count, count:10}} / 12/31 まで {kind:weekly, weekdays:[2], end:{kind:until, until:"2026-12-31"}}
statusNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses partial mutation, wholesale replacement of repeat, repeat removal via null or {kind:none}, notes deletion via null, and the status restriction on repeating TODOs. It stops short of auth, error, or return behavior, but covers the main mutation semantics.

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?

The description is compact and front-loaded, moving from the general update operation to key semantic caveats without wasted sentences.

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 7-parameter mutation tool with no annotations and no output schema, the description provides the crucial update semantics an agent needs. Minor gaps remain around id requirements and error/return behavior, but core invocation safety is covered.

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 only 43%, so the description must compensate. It adds valuable semantics for repeat, notes, and status, but does not explain id, due-time formatting, or sound choices beyond what the schema already provides.

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 (変える) and resource (TODO), enumerates the mutable fields, and distinguishes the tool from complete_todo and snooze_todo for repeating TODO status operations.

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 clearly explains partial-update behavior (渡した項目だけ変わる) and routes the agent away from using this tool to change status on repeating TODOs, naming complete_todo and snooze_todo as alternatives. It does not cover every sibling relationship, but the relevant exclusion is explicit.

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

Deploy Server

Other Tools