Skip to main content
Glama

Boundra — Payment Approval Gateway for AI Agents

request_policy_change

[For agents] Ask the user for a policy/budget change (e.g. 'raise daily budget from 50 to 80'). The request is queued for user approval; the user signs and publishes a new policy version. Agents can NEVER change policy directly.

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": {
      "agent_id": "<agent_id>",
      "request": "<request>",
      "reason": "<reason>"
    },
    "name": "request_policy_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesEvidence or explanation for why the change is needed
requestYesRequested policy or budget change in natural language
agent_idYesStable identifier of the agent requesting this operation

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / agent_id / description
      Added value: +"Stable identifier of the agent requesting this operation"
    • addedInput schema / properties / reason / description
      Added value: +"Evidence or explanation for why the change is needed"
    • addedInput schema / properties / request / description
      Added value: +"Requested policy or budget change in natural language"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false; the description adds genuinely new behavioral context by explaining the asynchronous user-approval workflow and that a new signed policy version results. It does not disclose duplicate-submission behavior (idempotentHint=false implies repeat calls create repeat requests) or latency, so it stops short of full transparency.

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?

Three short sentences, front-loaded with the action and the hard constraint. Every sentence carries distinct information: what to do, what happens next, and what is forbidden.

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?

An output schema exists, so return values need not be described, and the description covers the approval lifecycle and the no-direct-write constraint. Remaining gaps are minor: nothing about how long approval takes, what happens on rejection, or how to check status (though list_policy_requests covers the latter).

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 coverage is 100%, so the schema already documents agent_id, request, and reason. The description's example ('raise daily budget from 50 to 80') adds modest format guidance for the free-text request parameter, but says nothing about how reason is used or what makes an approval likely.

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?

States a specific verb and resource ('Ask the user for a policy/budget change') with a concrete example, and explicitly separates itself from direct policy mutation ('Agents can NEVER change policy directly'), which distinguishes it from set_policy in the sibling set.

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?

Makes the routing rule clear: agents cannot change policy themselves, so any desired budget/policy change must go through this request-and-approval path. It does not explicitly name set_policy or explain when a change is too small to warrant a request, but the core when-to-use condition is unambiguous.

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.