Skip to main content
Glama

Quantum Atlas Stripe X402 Agent Payment Hub

Update Delegated Key Policy

x402_update_delegate_key
Idempotent

Modify standing spend limits, route allowlist, or label on an active delegated subagent key (sbd_*) live without rotating its secret. Use this to tighten or expand ongoing budgets for an existing subagent; do not use this to mint a new key (use x402_issue_delegate_key), grant a single-use exception (use x402_decide_approval), or permanently disable a key (use x402_revoke_delegate_key). Requires a master sbk_* spend key; idempotent for identical policy payloads. Returns HTTP 403 for delegated callers and HTTP 404 if delegate_id is unknown.

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_id": "<delegate_id>"
    },
    "name": "x402_update_delegate_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoUpdated human-readable label for the delegated subagent key.
spend_keyNoMaster Stripe account spend key (format: sbk_<43+ chars>). Delegated subagent keys are rejected with HTTP 403. Optional if supplied via the x-atlas-spend-key HTTP header.
delegate_idYesUnique delegated subagent key identifier returned by x402_issue_delegate_key or x402_get_account (format: sbd_<16 hex chars>, e.g. sbd_1122334455667788).
allowed_routesNoRoute allowlist patterns restricting which capabilities the delegated key may invoke (supports exact routes like "POST /kb/search" or prefix wildcards like "GET /reality/*"). Omit or pass [] to allow all hub capabilities.
max_order_centsNoUpdated per-call spend cap in USD cents, or null to clear the per-call cap.
daily_budget_centsNoUpdated UTC daily budget cap in USD cents, or null to clear the daily cap.
total_budget_centsNoUpdated lifetime cumulative cap in USD cents, or null to clear the lifetime cap.

Output Schema

NameRequiredDescriptionDefault
okYesTrue when the delegate policy was updated.
delegateNoFull updated delegate policy and live spend counters.
delegate_idNoUpdated delegated key identifier (sbd_*).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it adds auth requirements (master sbk_* required, delegated keys get HTTP 403), unknown-id failure behavior (HTTP 404), and the key operational trait that policy changes take effect live without rotating the secret. Idempotency is restated more specifically than idempotentHint=true, and nothing contradicts readOnlyHint=false or destructiveHint=false.

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 sentences, zero waste: purpose first, then routing to alternatives, then preconditions and error codes. Every clause carries actionable information, and the most decision-relevant content (what it modifies and what it must not be used for) is front-loaded.

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

Completeness5/5

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

For a 7-parameter mutation tool with a full output schema and annotations covering the safety profile, this description supplies the remaining agent-critical facts: required credential class, live-effect semantics, sibling routing, and failure codes. Nothing needed to call it correctly is missing.

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 delegate_id, spend_key, allowed_routes, label, and the three cent-denominated caps including that null clears them. The description adds no syntactic or format guidance beyond that, so it sits at the documented baseline of 3.

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 (Modify) and precise resource (standing spend limits, route allowlist, label on an active delegated subagent key sbd_*) and immediately scopes it with 'live without rotating its secret.' The sibling set is explicitly partitioned, so an agent can distinguish this from issue/revoke/approve tools without opening a schema.

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

Usage Guidelines5/5

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

Gives an explicit when-to-use ('tighten or expand ongoing budgets for an existing subagent') and three explicit when-not-to-use cases, each paired with the correct alternative tool name (x402_issue_delegate_key for minting, x402_decide_approval for single-use exceptions, x402_revoke_delegate_key for permanent disable). It also names the prerequisite (a master sbk_* spend key).

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