Skip to main content
Glama

get_cards

Read-only

Retrieve cards from a Trello list or board, filter by open, archived, or all, and paginate large boards. Returns an array; optionally omit descriptions and labels to save space.

Instructions

Get the cards in a list, or on a board (provide exactly one of listId/boardId). Returns an array. For big boards paginate with limit and offset: the result is then {total, offset, returned, hasMore, cards}; call again with offset += limit while hasMore is true. filter: open (default), closed (archived) or all. compact drops descriptions and labels to save space. Reads up to 1000 cards.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_cards"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoISO 639-1 code of the language the user is writing in (e.g. en, ru, uk). Always pass it: server messages are returned in this language.
limitNoPage size; enables paginated output
filterNoopen
listIdNo
offsetNoHow many cards to skip (with limit)
boardIdNo
compactNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the return shape (bare array vs {total, offset, returned, hasMore, cards}), the archive filter default, and what compact removes. The trailing claim "Reads up to 1000 cards" is slightly at odds with the preceding pagination advice, leaving the total-vs-page cap ambiguous.

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?

Four dense sentences, each carrying distinct information, front-loaded with the scope constraint and ending with a size caveat. No restatement of the tool name or 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?

With no output schema, the description properly documents both possible return shapes and the loop needed to exhaust a large board, plus the safety-relevant archive filter. An agent has everything required to page correctly and pick the right scope.

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 coverage is only 43%, and the description compensates well: it explains the listId/boardId exclusivity, the limit/offset paging protocol including the hasMore loop, the three filter values and the default open, and the token-saving effect of compact. Only lang is left undiscussed, and the schema documents it fully.

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 ("Get the cards") plus the two scopes it operates over (a list or a board), which cleanly separates it from the sibling get_card (single) and get_lists. The scope is established in the first clause before any detail is given.

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?

Gives an explicit selection constraint ("provide exactly one of listId/boardId") and a concrete when-to-use path for pagination (call again with offset += limit while hasMore). It does not name an alternative for the single-card case, but the context is unambiguous without it.

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