Skip to main content
Glama

delete_comments

Remove comments from Todoist tasks to clean up project discussions and maintain organized workflows.

Instructions

Delete comments in Todoist

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes

Implementation Reference

  • Tool registration for 'delete_comments'. Defines the tool name, description, input schema requiring 'id', DELETE HTTP method to Todoist API endpoint '/comments/{id}', with idField and delete mode.
    createBatchApiHandler({
        name: 'delete_comments',
        description: 'Delete comments in Todoist',
        itemSchema: {
            id: z.string(),
        },
        method: 'DELETE',
        path: '/comments/{id}',
        idField: 'id',
        mode: 'delete',
    });
  • Generic handler creator for batch API operations. For 'delete_comments', it processes batch of items, resolves ID, constructs path '/comments/{id}', and executes todoistApi.delete(finalPath) for each valid item.
    export function createBatchApiHandler<T extends z.ZodRawShape>(
        options: {
            name: string;
            description: string;
            itemSchema: T;
            method: HttpMethod;
            mode?: 'read' | 'create' | 'update' | 'delete';
            idField?: string;
            nameField?: string;
            findByName?: (name: string, items: any[]) => any | undefined;
            validateItem?: (item: any) => { valid: boolean; error?: string };
        } & ( // Or we specify full path
            | {
                  path: string;
                  basePath?: never;
                  pathSuffix?: never;
              }
            // Or we specify base path and path suffix
            | {
                  path?: never;
                  basePath: string;
                  pathSuffix: string;
              }
        )
    ) {
        // Create basic description, we cant properly use 'anyOf' here so for now we will add info to description
        let finalDescription = options.description;
        const requiresIdOrName = options.idField && options.nameField && options.mode !== 'create';
    
        if (requiresIdOrName) {
            const requirementText = `\nEither '${options.idField}' or the '${options.nameField}' to identify the target.`;
            finalDescription += requirementText;
        }
    
        const itemSchemaObject = z.object(options.itemSchema);
    
        const enhancedItemSchema: z.ZodTypeAny = requiresIdOrName
            ? itemSchemaObject.refine(
                  (data: any) =>
                      data[options.idField!] !== undefined || data[options.nameField!] !== undefined,
                  {
                      message: `Either ${options.idField} or ${options.nameField} must be provided`,
                      path: [options.idField!, options.nameField!],
                  }
              )
            : itemSchemaObject;
    
        const batchSchema = z.object({
            items: z.array(enhancedItemSchema),
        });
    
        const handler = async (args: z.infer<typeof batchSchema>): Promise<any> => {
            const { items } = args;
    
            // For modes other than create, check if name lookup is needed
            let allItems: any[] = [];
    
            const needsNameLookup =
                options.mode !== 'create' &&
                options.nameField &&
                options.findByName &&
                items.some(item => item[options.nameField!] && !item[options.idField!]);
    
            if (needsNameLookup) {
                // Determine the base path for fetching all items
                // Example: /tasks from /tasks/{id}
                const lookupPath =
                    options.basePath || (options.path ? options.path.split('/{')[0] : '');
                allItems = await todoistApi.get(lookupPath, {});
            }
    
            const results = await Promise.all(
                items.map(async item => {
                    if (options.validateItem) {
                        const validation = options.validateItem(item);
    
                        if (!validation.valid) {
                            return {
                                success: false,
                                error: validation.error || 'Validation failed',
                                item,
                            };
                        }
                    }
    
                    try {
                        let finalPath = '';
                        const apiParams = { ...item };
    
                        // For modes where need id
                        if (options.mode !== 'create' && options.idField) {
                            let itemId = item[options.idField];
                            let matchedName = null;
                            let matchedContent = null;
    
                            // If no ID but name is provided, search by name
                            if (!itemId && item[options.nameField!] && options.findByName) {
                                const searchName = item[options.nameField!];
                                const matchedItem = options.findByName(searchName, allItems);
    
                                if (!matchedItem) {
                                    return {
                                        success: false,
                                        error: `Item not found with name: ${searchName}`,
                                        item,
                                    };
                                }
    
                                itemId = matchedItem.id;
                                matchedName = searchName;
                                matchedContent = matchedItem.content;
                            }
    
                            if (!itemId) {
                                return {
                                    success: false,
                                    error: `Either ${options.idField} or ${options.nameField} must be provided`,
                                    item,
                                };
                            }
    
                            // Apply security validation to itemId before using in path
                            const safeItemId = validatePathParameter(itemId, options.idField || 'id');
    
                            if (options.basePath && options.pathSuffix) {
                                finalPath = `${options.basePath}${options.pathSuffix.replace('{id}', safeItemId)}`;
                            } else if (options.path) {
                                finalPath = options.path.replace('{id}', safeItemId);
                            }
    
                            delete apiParams[options.idField];
                            if (options.nameField) {
                                delete apiParams[options.nameField];
                            }
    
                            let result;
                            switch (options.method) {
                                case 'GET':
                                    result = await todoistApi.get(finalPath, apiParams);
                                    break;
                                case 'POST':
                                    result = await todoistApi.post(finalPath, apiParams);
                                    break;
                                case 'DELETE':
                                    result = await todoistApi.delete(finalPath);
                                    break;
                            }
    
                            const response: any = {
                                success: true,
                                id: itemId,
                                result,
                            };
    
                            if (matchedName) {
                                response.found_by_name = matchedName;
                                response.matched_content = matchedContent;
                            }
    
                            return response;
                        }
                        // Create mode
                        else {
                            finalPath = options.path || options.basePath || '';
    
                            let result;
                            switch (options.method) {
                                case 'GET':
                                    result = await todoistApi.get(finalPath, apiParams);
                                    break;
                                case 'POST':
                                    result = await todoistApi.post(finalPath, apiParams);
                                    break;
                                case 'DELETE':
                                    result = await todoistApi.delete(finalPath);
                                    break;
                            }
    
                            return {
                                success: true,
                                created_item: result,
                            };
                        }
                    } catch (error) {
                        return {
                            success: false,
                            error: error instanceof Error ? error.message : String(error),
                            item,
                        };
                    }
                })
            );
    
            const successCount = results.filter(r => r.success).length;
            return {
                success: successCount === items.length,
                summary: {
                    total: items.length,
                    succeeded: successCount,
                    failed: items.length - successCount,
                },
                results,
            };
        };
    
        return createHandler(options.name, finalDescription, batchSchema.shape, handler);
    }
  • Input schema for delete_comments tool: requires 'id' string for the comment to delete. Used in batch as array of items.
    itemSchema: {
        id: z.string(),
    },
  • Helper function that wraps the tool handler with MCP formatting and error handling, and registers it via server.tool.
    export function createHandler<T extends z.ZodRawShape>(
        name: string,
        description: string,
        paramsSchema: T,
        handler: (args: HandlerArgs<T>) => Promise<any>
    ): void {
        const mcpToolCallback = async (args: HandlerArgs<T>): Promise<CallToolResult> => {
            try {
                const result = await handler(args);
    
                return {
                    content: [
                        {
                            type: 'text',
                            text: JSON.stringify(result ?? null, null, 2).trim(),
                        },
                    ],
                };
            } catch (error) {
                const errorMessage = error instanceof Error ? error.message : String(error);
    
                console.error(`Error in tool ${name}:`, error);
    
                return {
                    isError: true,
                    content: [
                        {
                            type: 'text',
                            text: `Error executing tool '${name}': ${errorMessage}`,
                        },
                    ],
                };
            }
        };
    
        // Crazy cast, if you can do it better, please, let me knows
        server.tool(name, description, paramsSchema, mcpToolCallback as unknown as ToolCallback<T>);
    }
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('Delete') which implies a destructive mutation, but doesn't specify permissions required, whether deletion is permanent/reversible, rate limits, or what happens on success/failure. This leaves significant gaps for a destructive operation.

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 extremely concise at just three words, with zero wasted text. It's front-loaded with the essential action and resource. Every word earns its place, though this conciseness comes at the cost of completeness.

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

Completeness2/5

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

For a destructive mutation tool with no annotations, 0% schema description coverage, and no output schema, the description is inadequate. It doesn't explain what 'comments' are in Todoist context, doesn't cover parameters or return values, and provides minimal behavioral context. The tool needs more explanation given its complexity and potential impact.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate but provides no parameter information. The schema shows one parameter 'items' (an array of objects with 'id'), but the description doesn't explain what 'items' represents, what 'id' refers to, or format requirements. This leaves parameters largely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete') and resource ('comments in Todoist'), making the purpose immediately understandable. It distinguishes from sibling tools like 'create_comments' and 'update_comments' by specifying deletion, though it doesn't explicitly differentiate from other deletion tools like 'delete_labels' or 'delete_tasks'.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing comment IDs), exclusions, or comparisons to siblings like 'delete_tasks' or 'update_comments'. Usage is implied by the name but not explicitly stated.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/stanislavlysenko0912/todoist-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server