Skip to main content
Glama

Update card fields

kanbini_update_card

Update one or more card fields by patching only the values you want to change, including title, description, due date, priority, completion, cover, and repeat settings.

Instructions

Patch one or more card fields. title and description are strings; description accepts Markdown - use real line breaks for paragraphs and lists (a literal backslash-n renders as text, not a break). due is a YYYY-MM-DD day (or dueAt, epoch ms), null clears it. completed toggles the checkbox. coverAttachmentId is the attachment id to use as the cover banner, or null to clear. priority is one of 'low' | 'medium' | 'high' | 'urgent', or null to clear. collapsed only changes how the card is DRAWN in its list: true shows it compact, false keeps it full even in a compact list, null follows the list's cardDensity. It hides nothing from you, so change it only when the user asks for a tidier board. repeat makes the card repeat: { unit: 'day' | 'week' | 'month' | 'year', every: 1-99 } (e.g. { unit: 'week', every: 2 } for every two weeks), or null to stop. When a repeating card is completed, the app adds the next one to the list it was worked in, due one repeat after the old due date (always in the future), with the same title, description, labels, priority, and unticked checklists; the rule moves to the new card. Omit fields you do not want to change. Labels: kanbini_set_card_labels. A card can be given by its id, or by its number (#142, as shown on the card) with boardId (the id or name of the board it is on).

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>",
      "patch": "<patch>"
    },
    "name": "kanbini_update_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
patchYes
boardIdNoThe board's id or exact name. Needed when you name a card by number (#142) or a list / label by name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.17.0
    • changedInput schema / properties / boardId / description
      Previous value: -"Only when a card is given by number (#142): the board it is on"New value: +"The board's id or exact name. Needed when you name a card by number (#142) or a list / label by name."
    • addedInput schema / properties / patch / properties / due
      Added value: +{
      +  "anyOf": [
      +    {
      +      "description": "Local calendar day, YYYY-MM-DD",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
  2. Changed1 schema field changedv0.15.0
    • addedInput schema / properties / boardId
      Added value: +{
      +  "description": "Only when a card is given by number (#142): the board it is on",
      +  "type": "string"
      +}
  3. First observedv0.13.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses null-as-clear semantics, Markdown escaping pitfalls, that `collapsed` is purely a rendering concern and hides nothing, and the non-obvious side effect that completing a repeating card creates a new card with copied fields and moves the rule. It does not say what the call returns or how partial failures/validation errors behave, so it is strong but not complete.

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 core action and the "omit unchanged fields" rule are front-loaded, and most sentences carry unique semantics. The verbose stretch is the repeat/completion paragraph and the collapsed explanation, which are long but correspond to genuinely non-obvious behavior rather than filler.

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

Completeness5/5

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

For a nested-object patch tool with ten optional fields, no annotations, and no output schema, the description supplies everything an agent needs: field semantics, clearing behavior, addressing rules, formatting caveats, and the repeat side effect. No critical decision-relevant information is missing.

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?

Schema description coverage is only 33%, but the description compensates by giving meaning for essentially every patch field: title/description types and Markdown handling, due as YYYY-MM-DD vs dueAt in epoch ms, completed as a checkbox toggle, coverAttachmentId clearing, the priority enum, the collapsed tri-state, and the repeat object shape with a worked example. It also explains id-vs-number-plus-boardId addressing.

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?

"Patch one or more card fields" gives a specific verb (patch, i.e. partial update) and resource (card), and the closing sentence routes labels to kanbini_set_card_labels, distinguishing it from that sibling. An agent can tell this apart from kanbini_create_card or kanbini_move_card without opening any 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?

It states the key usage rule explicitly: "Omit fields you do not want to change," and gives a concrete alternative for label changes (kanbini_set_card_labels). It also explains how to address the card (id, or number plus boardId). It stops short of naming alternatives for moving/archiving/completing via other tools, so it stops at clear context rather than a full when/when-not matrix.

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