Skip to main content
Glama

Create a mandate

mandate_create

Creates a mandate and the out-of-band approval link for the owner. Never: Activate production. Free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "delegate": "<delegate>",
      "scopes": "<scopes>"
    },
    "name": "mandate_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopesYesWhat the owner allows you to do, at least one, e.g. ["intake.classify", "job.create"].
channelNoWhere the owner gets the approval link, e.g. {"type": "whatsapp", "number_e164": "+41791234567"}. Leave out to get the link back.
paid_byNoWho pays the platform fees. business (default): billed to the business. agent: from your own credit; send your jfa_ key.
sandboxNotrue: a test mandate with sample data, approved at once, no fees, valid one day. The whole flow runs, payment is simulated, nothing reaches a real business.
businessNoThe business the owner runs, as far as you know it, e.g. {"name": "Muster Sanitär", "trade": "plumbing", "contact": "owner@example.ch"}.
delegateYesYou, the agent: your name and optionally who built you, e.g. {"name": "Dispatch helper", "vendor": "Anthropic"}.
expires_in_daysNoDays until the mandate ends, 1 to 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / business / description
      Added value: +"The business the owner runs, as far as you know it, e.g. {\"name\": \"Muster Sanitär\", \"trade\": \"plumbing\", \"contact\": \"owner@example.ch\"}."
    • addedInput schema / properties / channel / description
      Added value: +"Where the owner gets the approval link, e.g. {\"type\": \"whatsapp\", \"number_e164\": \"+41791234567\"}. Leave out to get the link back."
    • addedInput schema / properties / delegate / description
      Added value: +"You, the agent: your name and optionally who built you, e.g. {\"name\": \"Dispatch helper\", \"vendor\": \"Anthropic\"}."
    • addedInput schema / properties / expires_in_days / description
      Added value: +"Days until the mandate ends, 1 to 30."
    • addedInput schema / properties / scopes / description
      Added value: +"What the owner allows you to do, at least one, e.g. [\"intake.classify\", \"job.create\"]."
  2. Changed1 schema field changed
    • addedInput schema / properties / sandbox
      Added value: +{
      +  "description": "true: a test mandate with sample data, approved at once, no fees, valid one day. The whole flow runs, payment is simulated, nothing reaches a real business.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

B3.2/5.0
Behavior3/5

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

With annotations already declaring non-read-only, non-destructive, non-idempotent behavior, the description adds useful context: the owner receives an out-of-band approval link and production activation is excluded. However, 'Free.' is vague and may conflict with the schema's paid_by field, which describes business or agent-paid fees.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise and front-loads the core action. However, the fragments 'Never: Activate production. Free.' are terse enough to be ambiguous, especially 'Free.'

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?

For a tool with seven parameters, nested objects, and no output schema, the description omits important context such as what happens after the approval link is sent and what the tool returns. The rich schema compensates for much of this, but the description leaves material gaps.

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 seven parameters in detail. The description adds no parameter-level information, consistent with the baseline for fully documented schemas.

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 a specific verb and resource: creating a mandate and its out-of-band approval link for the owner. It does not differentiate this from siblings such as register_agent, but the action itself is unambiguous.

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?

There is no guidance on when to use this tool versus alternatives in the sibling list, nor are prerequisites or exclusions stated. 'Never: Activate production' is a scope limitation, not usage selection guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources