Sous

Overview Schema Source Related Servers Discussions Admin

Optional: Renew a standing order (with drift check)

renew_standing_order

Destructive

Renew a weekly standing order by fetching a live quote, checking past renewals for quantity, price, product, or reliability drift, then placing the order; drift holds it for human approval.

Instructions

Renew this week's standing order: live quote, drift check against past renewals, then the order.

amounts: this week's amount per item, in item order, if it differs from the usual (omit for the usual). The gateway compares with the median of recent renewals: quantity creep, cost or price drift, a different product, new Terminal or reliability issues. Any drift puts the order on hold for a human (pending_approval); tell the buyer drift.summary and share order.approval_url. delivery_date defaults to the next delivery day. agent_id: optional when your credential covers the standing order's mandate (see my_mandates). agent_token: only if you can't send the Authorization: Bearer header and the mandate requires agent auth.

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": {
      "standing_id": "<standing_id>"
    },
    "name": "renew_standing_order"
  }
}

Input Schema

Name	Required	Description	Default
`amounts`	No
`agent_id`	No
`rationale`	No
`agent_token`	No
`standing_id`	Yes
`delivery_date`	No

Output Schema

Name	Required	Description
`drift`	Yes	{findings[], summary, baseline}
`order`	Yes
`renewal`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 15, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the description does not need to re-state the safety profile. It does add genuinely new behavior: a drift check against the median of recent renewals covering quantity creep, cost/price drift, product changes, and Terminal/reliability issues, with any drift resulting in pending_approval and an approval_url the agent should surface. What it omits is retry semantics for a non-idempotent money-moving call, which the annotations flag but the prose never reinforces.

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 purpose is front-loaded in one sentence, followed by compact parameter notes and a final line on delivery_date. Wording is dense but nearly every clause carries information; the only slack is the slightly clipped 'then the order' and the parameter notes being ordered differently from the schema.

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?

With an output schema present, return-value explanation is unnecessary, yet the description still calls out the two response fields an agent must act on (drift.summary and order.approval_url). Auth prerequisites, default behavior for amounts and delivery_date, and the approval hold path are all covered. A brief note on what a successful non-drift renewal produces, or on retry safety, would close the remaining gap for a destructive financial operation.

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 carries the full burden, and it does so for four of six parameters: amounts (per item, in item order, omit for the usual), delivery_date (defaults to the next delivery day), agent_id (optional under a covering mandate), and agent_token (fallback for missing Bearer header). Only rationale and standing_id are left unaddressed, and standing_id is self-evident from the tool name.

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 opening sentence names a specific verb and resource and lays out the pipeline: 'Renew this week's standing order: live quote, drift check against past renewals, then the order.' An agent immediately knows this is a renewal operation that re-quotes and validates before placing. It does not explicitly contrast itself with create_standing_order or place_order, which are the most plausible confusions.

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?

Usage context is clear: this renews the current week's order, and drift routes the order to human approval rather than completing it. The description also gives conditional guidance for optional auth ('agent_id: optional when your credential covers the standing order's mandate (see my_mandates)' and 'agent_token: only if you can't send the Authorization: Bearer header'), pointing the agent at a sibling for prerequisites. It stops short of stating when to prefer create_standing_order or place_order instead.

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

Deploy Server