Skip to main content
Glama

Attach a file to a card

kanbini_add_attachment

Attach a file to a Kanbini card using a local path or inline text/base64 content; returns stored attachment details including ID and MIME type.

Instructions

Attach a file to a card, from ONE of two sources. (1) path: an absolute path to a local file, which the app copies in (up to 100 MB) - use this for files that already exist on disk. (2) filename + content: inline data you produce yourself, as encoding: "utf8" text (the default - notes, CSV, code) or encoding: "base64" for small binaries (up to 10 MB decoded). The filename's extension sets the file type; unsafe characters are replaced. Returns the stored attachment ({ id, filename, mime, size, ... , boardId }). To show an image as the card's cover, pass the returned id as coverAttachmentId to kanbini_update_card. 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": {
      "cardId": "<cardId>"
    },
    "name": "kanbini_add_attachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
cardIdYes
boardIdNoThe board id or name, when the card is given by number (#142)
contentNo
encodingNo
filenameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field 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 id or name, when the card is given by number (#142)"
  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

A4.7/5.0
Behavior4/5

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

With no annotations present, the description carries the full burden and does well: it discloses size ceilings (100 MB for path, 10 MB decoded for base64), that the app copies the local file in, that unsafe filename characters are sanitized, and that the extension determines the mime type. It does not cover permissions/auth requirements, overwrite behavior for duplicate filenames, or what happens when the path is missing or too large, which keeps it short of a 5.

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 purpose sentence, then a clearly numbered (1)/(2) source breakdown, then return value, then a secondary use case. Dense but every clause carries information; the only mild cost is that it is a single unbroken paragraph rather than visibly separated sections.

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 six-parameter mutation tool with no annotations and no output schema, the description supplies the constraints (size limits, encoding choice), the identifier conventions (card by id vs number plus boardId), and the return shape ({ id, filename, mime, size, ..., boardId }). An agent has everything needed to construct a valid call and reuse the result without further inspection.

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 17%, so the description must compensate, and it does for essentially every parameter: `path` (absolute local path), `filename` (extension drives file type, characters sanitized), `content` (inline data, tied to encoding), `encoding` (utf8 default vs base64 for binaries), `cardId` (id or `#142` style number), and `boardId` (required when the card is given by number, and it accepts an id or a board name). That is meaningful semantics well beyond the bare schema.

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 and resource ('Attach a file to a card') and immediately enumerates the two mutually exclusive sources, so an agent knows exactly which operation this is and how it differs from a plain card update. The follow-on pointer to kanbini_update_card for cover assignment further distinguishes its scope from sibling mutation tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance for each mode: `path` for files that already exist on disk, inline `filename`+`content` for data the agent produces itself, with utf8 for text and base64 reserved for small binaries. It also names the explicit follow-up path (pass the returned id as `coverAttachmentId` to kanbini_update_card), which is the only realistic cross-tool alternative here.

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