Skip to main content
Glama

middleware_submit_transaction

DestructiveIdempotent

Middleware admin only: submit a middleware transaction using action/input from middleware_get_capabilities. For account actions the selected enabled middleware account is used. For domain actions supply the middleware domain_id. Choose account_id from middleware_get_capabilities when several accounts are enabled. Every submission needs a stable idempotency_key: retry an identical request with the SAME key. 202/queued means accepted, not completed; poll middleware_get_transaction. Paid or destructive actions require explicit user intent. These operator orders use the linked tenant's AIvikings prepaid wallet and do not update the local domain portfolio.

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": {
      "action": "<action>",
      "input": "<input>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "middleware_submit_transaction"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes
actionYes
domain_idNo
account_idNo
customer_idNo
idempotency_keyYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / customer_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Customer Id"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=true, so the safety profile is known, yet the description adds real context beyond them: 202/queued means accepted-not-completed, identical retries must reuse the same key, charges hit the linked tenant's AIvikings prepaid wallet, and the local domain portfolio is not updated. The only notable omissions are what a failure/error response looks like and whether submissions are rate limited.

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 audience restriction and submit verb are front-loaded, and each subsequent sentence contributes a distinct operational fact (routing, idempotency, async result, billing, portfolio side effect) with no filler or repetition of the schema. Density is high, but nothing could be cut without losing guidance an agent needs.

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?

For a destructive, open-world, async mutation tool this covers the essentials: prerequisites, idempotency discipline, queued-result interpretation, follow-up polling, billing destination and side-effect scope. With an output schema present it needn't detail return values, though the unmentioned customer_id and absence of failure-mode guidance keep it just short of fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning and largely does: it explains action and input come from capabilities, domain_id is required for domain actions, account_id for multi-account selection, and idempotency_key must stay stable across retries. The sixth parameter, customer_id, is never mentioned, which is the main remaining coverage gap for a nested free-form input object.

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 ("submit a middleware transaction") plus the audience restriction ("Middleware admin only"), and immediately distinguishes itself from read-only siblings by pointing at middleware_get_capabilities as the source of action/input. An agent can tell this is the single write/execute path versus the family of middleware_get_* readers.

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 explicit routing rules: get action/input from middleware_get_capabilities, supply domain_id for domain actions, choose account_id only when several accounts are enabled, and poll middleware_get_transaction after submission. It also states the precondition that paid or destructive actions need explicit user intent, which is genuine when-to-use guidance rather than restated mechanics.

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.