Skip to main content
Glama

request_approval

Request human approval for AI agent actions before execution, providing context and optional callback for decisions.

Instructions

Ask a human to approve or reject an action. Returns an approval ID to poll.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYesThe question or action to approve
contextNoAdditional context for the human reviewer
callback_urlNoOptional URL to notify when decided

Implementation Reference

  • The handler logic for request_approval which calls the remote /approve endpoint.
    case 'request_approval':
      result = await call('POST', '/approve', args);
      return {
        content: [{
          type: 'text',
          text: `Approval request submitted (ID: ${result.id}). Status: pending.\nPoll with check_approval("${result.id}") to see the human's decision.`,
        }],
      };
  • Definition and input schema for the request_approval tool.
      name: 'request_approval',
      description: 'Ask a human to approve or reject an action. Returns an approval ID to poll.',
      inputSchema: {
        type: 'object',
        properties: {
          question: { type: 'string', description: 'The question or action to approve' },
          context: { type: 'string', description: 'Additional context for the human reviewer' },
          callback_url: { type: 'string', description: 'Optional URL to notify when decided' },
        },
        required: ['question'],
      },
    },
Behavior4/5

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

With no annotations provided, the description carries the full burden. It successfully discloses the human-in-the-loop interaction and the async pattern (returns ID to poll), but omits timeout behavior, idempotency, or what happens when approval is denied.

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?

Two sentences, zero waste. Front-loaded with the core action ('Ask a human') followed immediately by the return value behavior. Every word earns its place.

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

Completeness4/5

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

Given the 100% schema coverage and lack of annotations, the description adequately covers the core workflow. However, it could strengthen completeness by explicitly referencing the 'check_approval' sibling relationship or describing error scenarios.

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 structured documentation already clearly defines all three parameters (question, context, callback_url). The description doesn't add parameter-specific semantics beyond what's in the schema, which is acceptable given the high 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?

Description uses specific verbs ('Ask', 'approve or reject') and identifies the resource (human) clearly. It distinguishes from siblings like 'check_approval' by emphasizing the request initiation aspect versus checking status.

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 'Returns an approval ID to poll' implies an asynchronous workflow and hints at using 'check_approval' for polling, but it doesn't explicitly state when to use this tool versus alternatives or explicitly name the sibling polling tool.

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/andrewpetecoleman-cloud/agentmemo-mcp'

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