Skip to main content
Glama

doc_disconnect

Remove documents from an AI agent's knowledge base to manage content access and update information sources.

Instructions

Disconnect/unlink a document from a Pickaxe agent, removing it from the agent's knowledge base.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
studioNoStudio name to use. Available: STAGING, MAIN, DEV, PRODUCTION. Default: PRODUCTION
documentIdYesThe document ID to disconnect
pickaxeIdYesThe Pickaxe agent ID to disconnect the document from

Implementation Reference

  • Handler implementation for the 'doc_disconnect' tool. It makes a POST request to the Pickaxe API endpoint '/studio/document/disconnect' with the documentId and pickaxeId parameters to unlink the document from the agent.
    case "doc_disconnect": {
      const result = await pickaxeRequest("/studio/document/disconnect", "POST", {
        documentId: args.documentId,
        pickaxeId: args.pickaxeId,
      }, studio);
      return JSON.stringify(result, null, 2);
  • Input schema definition for the 'doc_disconnect' tool, specifying parameters: studio (optional), documentId (required), pickaxeId (required).
    {
      name: "doc_disconnect",
      description: "Disconnect/unlink a document from a Pickaxe agent, removing it from the agent's knowledge base.",
      inputSchema: {
        type: "object",
        properties: {
          studio: studioParam,
          documentId: {
            type: "string",
            description: "The document ID to disconnect",
          },
          pickaxeId: {
            type: "string",
            description: "The Pickaxe agent ID to disconnect the document from",
          },
        },
        required: ["documentId", "pickaxeId"],
      },
    },
  • src/index.ts:616-618 (registration)
    Registration of the tool list handler, which returns the array of tools including 'doc_disconnect'.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return { tools };
    });
  • src/index.ts:621-636 (registration)
    Registration of the call tool handler, which dispatches to executeTool based on tool name, handling 'doc_disconnect' via the switch case.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: args } = request.params;
    
      try {
        const result = await executeTool(name, (args as Record<string, unknown>) ?? {});
        return {
          content: [{ type: "text", text: result }],
        };
      } catch (error) {
        const errorMessage = error instanceof Error ? error.message : String(error);
        return {
          content: [{ type: "text", text: `Error: ${errorMessage}` }],
          isError: true,
        };
      }
    });
Behavior2/5

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

No annotations are provided, so the description carries full burden. It states the action is to 'disconnect/unlink' and remove from knowledge base, implying a mutation, but doesn't disclose behavioral traits like whether this is reversible, requires specific permissions, has side effects on the document or agent, or what the response looks like (e.g., success/failure).

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, efficient sentence that front-loads the core action and effect. Every word earns its place, with no redundancy or unnecessary details, making it easy to parse quickly.

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?

Given the complexity (a mutation tool with no annotations and no output schema), the description is incomplete. It lacks information on behavioral context (e.g., reversibility, permissions), response format, and usage guidelines, leaving gaps for an AI agent to invoke it correctly.

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 documents all three parameters (studio, documentId, pickaxeId) with their types and descriptions. The description doesn't add any meaning beyond what the schema provides, such as explaining relationships between parameters (e.g., documentId and pickaxeId must correspond to an existing link).

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 clearly states the action ('disconnect/unlink'), the resource ('a document from a Pickaxe agent'), and the effect ('removing it from the agent's knowledge base'). It distinguishes from siblings like doc_connect (linking) and doc_delete (deleting the document entirely).

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?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., the document must be linked first), exclusions, or comparisons to siblings like doc_delete (which might remove the document entirely versus just unlinking).

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/aplaceforallmystuff/mcp-pickaxe'

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