Skip to main content
Glama

Send an ordered tool back

revise_order

Send a tool you ordered from x402 Forge back with one sentence about what is missing or should change. Free. Needs the revision_key from your order. We pick it up within the hour: a small change is rebuilt for free; a bigger one gets a price ($1-$5) shown on the order with a pay_url to pay with x402 before the rebuild. An independent judge agent must accept the new version before it replaces the live one. Up to 3 times per order.

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": {
      "order_id": "<order_id>",
      "request": "<request>",
      "revision_key": "<revision_key>"
    },
    "name": "revise_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYesWhat is missing or should change, 10-400 characters
order_idYesord_...
revision_keyYesrk_... from the order's 201 answer

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does most of it: free small changes, a $1-$5 charge for larger ones surfaced as a pay_url that must be paid with x402 before rebuild, an independent judge gate before the live version is replaced, and a 3-per-order cap. It does not say what the immediate call returns (async confirmation vs. synchronous result) or what happens when the judge rejects a revision.

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?

It is front-loaded with the action and the free status before the pricing and judging mechanics, and every sentence carries information an agent would otherwise have to discover. The pricing/judge sentence is dense and could be split, but nothing is truly redundant.

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 multi-stage workflow tool with no output schema and no annotations, the description covers cost, payment prerequisite, approval gate, and rate limit — the facts most likely to cause a failed or misused call. The remaining gap is the shape of the immediate response and the rejection path.

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 all three parameters are already documented, which sets the baseline at 3. The description adds only light context — that `request` is a one-sentence statement of what is missing and that `revision_key` comes from the order — and never mentions `order_id` beyond implying the referenced order.

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?

"Send a tool you ordered ... back with one sentence about what is missing or should change" gives a specific verb (revise/return), a specific resource (a tool previously ordered), and the required payload shape. An agent can distinguish it from order_product or buy_product because it presupposes an existing order and its revision_key.

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?

It states the triggering context (you ordered a tool and something is missing or should change), the prerequisite (revision_key from your order), and a hard limit (up to 3 times per order). It stops short of naming an alternative path, e.g. when to use report_problem instead, so it is clear but not fully routing.

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