Skip to main content
Glama

create_card

Add tasks, ideas, or items to Trello lists to organize your workflow. Create cards with titles, descriptions, due dates, assignments, and labels for project management.

Instructions

Create a new card in a Trello list. Use this to add tasks, ideas, or items to your workflow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
apiKeyYesTrello API key (automatically provided by Claude.app from your stored credentials)
tokenYesTrello API token (automatically provided by Claude.app from your stored credentials)
nameYesName/title of the card (what the task or item is about)
descNoOptional detailed description of the card
idListYesID of the list where the card will be created (you can get this from get_lists)
posNoPosition in the list: "top", "bottom", or specific number
dueNoOptional due date for the card (ISO 8601 format, e.g., "2024-12-31T23:59:59Z")
idMembersNoOptional array of member IDs to assign to the card
idLabelsNoOptional array of label IDs to categorize the card

Implementation Reference

  • The main handler for the 'create_card' tool, responsible for validating input, calling the Trello client, and formatting the response.
    export async function handleCreateCard(args: unknown) {
      try {
        const cardData = validateCreateCard(args);
        const { apiKey, token, ...createData } = cardData;
        
        const client = new TrelloClient({ apiKey, token });
        const response = await client.createCard(createData);
        const card = response.data;
        
        const result = {
          summary: `Created card: ${card.name}`,
          card: {
            id: card.id,
            name: card.name,
            description: card.desc || 'No description',
            url: card.shortUrl,
            listId: card.idList,
            boardId: card.idBoard,
            position: card.pos,
            due: card.due,
            closed: card.closed,
            labels: card.labels?.map(label => ({
              id: label.id,
              name: label.name,
              color: label.color
            })) || [],
            members: card.members?.map(member => ({
              id: member.id,
              fullName: member.fullName,
              username: member.username
            })) || []
          },
          rateLimit: response.rateLimit
        };
        
        return {
          content: [
            {
              type: 'text' as const,
              text: JSON.stringify(result, null, 2)
            }
          ]
        };
      } catch (error) {
        const errorMessage = error instanceof z.ZodError 
          ? formatValidationError(error)
          : error instanceof Error 
            ? error.message 
            : 'Unknown error occurred';
            
        return {
          content: [
            {
              type: 'text' as const,
              text: `Error creating card: ${errorMessage}`
            }
          ],
          isError: true
        };
      }
    }
  • The definition of the 'create_card' tool, including its schema and description.
    export const createCardTool: Tool = {
      name: 'create_card',
      description: 'Create a new card in a Trello list. Use this to add tasks, ideas, or items to your workflow.',
      inputSchema: {
        type: 'object',
        properties: {
          apiKey: {
            type: 'string',
            description: 'Trello API key (automatically provided by Claude.app from your stored credentials)'
          },
          token: {
            type: 'string',
            description: 'Trello API token (automatically provided by Claude.app from your stored credentials)'
          },
          name: {
            type: 'string',
            description: 'Name/title of the card (what the task or item is about)'
          },
          desc: {
            type: 'string',
            description: 'Optional detailed description of the card'
          },
          idList: {
            type: 'string',
            description: 'ID of the list where the card will be created (you can get this from get_lists)',
            pattern: '^[a-f0-9]{24}$'
          },
          pos: {
            oneOf: [
              { type: 'number', minimum: 0 },
              { type: 'string', enum: ['top', 'bottom'] }
            ],
            description: 'Position in the list: "top", "bottom", or specific number'
          },
          due: {
            type: 'string',
            format: 'date-time',
            description: 'Optional due date for the card (ISO 8601 format, e.g., "2024-12-31T23:59:59Z")'
          },
          idMembers: {
            type: 'array',
            items: {
              type: 'string',
              pattern: '^[a-f0-9]{24}$'
            },
            description: 'Optional array of member IDs to assign to the card'
          },
          idLabels: {
            type: 'array',
            items: {
              type: 'string',
              pattern: '^[a-f0-9]{24}$'
            },
            description: 'Optional array of label IDs to categorize the card'
          }
        },
        required: ['apiKey', 'token', 'name', 'idList']
      }
    };

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that it creates a card, which implies a mutation, but it does not mention required permissions, reversibility, or what the response will contain. For a write operation, this is a significant gap.

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 a single, concise sentence that immediately conveys the action and purpose. It is front-loaded and wastes no words.

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

Completeness3/5

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

The schema is thorough, covering all 9 parameters with descriptions, which compensates somewhat. However, with no output schema, the description does not mention what the tool returns or any post-condition, leaving some contextual gaps for a creation tool.

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 description coverage is 100%, so the schema already explains all parameters. The description adds no new parameter information beyond contextualizing the overall purpose, which is the baseline score for full schema coverage.

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 uses a specific verb ('Create'), names the exact resource ('a new card in a Trello list'), and states the intended use ('add tasks, ideas, or items to your workflow'). This distinguishes it from sibling tools like create_board or update_card.

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?

The phrase 'Use this to add tasks, ideas, or items to your workflow' provides clear context for when to invoke the tool. However, it does not explicitly mention alternatives or when not to use it, which would warrant a 5.

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