Skip to main content
Glama

How to cancel a subscription

get_exit_plan
Read-onlyIdempotent

Use when the user wants to cancel, unsubscribe from, pause or pay less for something they subscribe to: streaming, music, news, dating, cloud storage, AI tools, apps or business software ('cancel YouTube TV', 'how do I get out of Adobe'). For a retention offer they hold, use prepare_negotiation. Returns Stackcut's exit plan: every way to cancel by who bills them (the company, Apple, Google Play, a partner or a contract), the steps with the words to expect on screen, when access ends, notice periods, fees and refunds, what to export first, cheaper ways to keep it, and notes for an agent, each fact sourced to the vendor's own page with a check date. Pass billed_by when known (the name on their card statement or receipt) and renewal_date to get the last safe day to cancel. Never cancel for the user without their go-ahead: they sign in, see any offer, and confirm the final step. Stackcut stores the arguments of tool calls to improve its recommendations (vendor names, prices, seats, features, usage numbers, billing amounts and project descriptions; account keys only as a one-way hash, billing and validation sources not at all; never IP addresses). Tool results are summarized; exit tools log only result counts, qualification flags and public evidence statuses, not answer contents. Don't send personal data or secrets.

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": {
      "service": "<service>"
    },
    "name": "get_exit_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNo
marketNoThe user's country, e.g. DE: when Stackcut has a guide checked for that market (JP, DE, BR, MX, NL), local_guide points to it
regionNoe.g. 'CA' (California)
serviceYesThe subscription, e.g. 'YouTube TV', 'Adobe Creative Cloud', 'disneyplus.com'
contractNo
billed_byNoWho charges them (card statement or receipt): the company (direct_web; direct_app in its app), Apple, Google Play, Amazon, Roku, PayPal, a phone or TV provider, a partner or a contract. Omit or 'unknown' for every route and the question to ask. Short words are aliases
start_dateNoContract start
months_leftNoMonthly payments left
renewal_dateNoNext renewal date, YYYY-MM-DD: adds the last safe day to cancel from the documented notice period
monthly_priceNoUSD a month: estimates an early termination fee
months_elapsedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / contract
      Added value: +{
      +  "enum": [
      +    "annual_paid_monthly",
      +    "annual_prepaid",
      +    "month_to_month"
      +  ],
      +  "maxLength": 2000,
      +  "type": "string"
      +}
    • changedInput schema / properties / monthly_price / description
      Previous value: -"USD a month: with renewal_date or months_left, estimates an early termination fee"New value: +"USD a month: estimates an early termination fee"
    • addedInput schema / properties / months_elapsed
      Added value: +{
      +  "maximum": 600,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / months_left / description
      Previous value: -"Monthly payments left (else from renewal_date)"New value: +"Monthly payments left"
    • addedInput schema / properties / region
      Added value: +{
      +  "description": "e.g. 'CA' (California)",
      +  "maxLength": 60,
      +  "type": "string"
      +}
    • addedInput schema / properties / start_date
      Added value: +{
      +  "description": "Contract start",
      +  "maxLength": 2000,
      +  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / market / description
      Added value: +"The user's country, e.g. DE: when Stackcut has a guide checked for that market (JP, DE, BR, MX, NL), local_guide points to it"
  3. Changed2 schema fields changed
    • addedInput schema / properties / goal
      Added value: +{
      +  "enum": [
      +    "cancel",
      +    "pay_less",
      +    "renegotiate"
      +  ],
      +  "maxLength": 2000,
      +  "type": "string"
      +}
    • addedInput schema / properties / market
      Added value: +{
      +  "maxLength": 2000,
      +  "pattern": "^[A-Z]{2}$",
      +  "type": "string"
      +}
  4. Changed4 schema fields changed
    • changedInput schema / properties / billed_by / description
      Previous value: -"Who charges them (their card statement or receipt says): the company itself (direct_web), Apple, Google Play, Amazon, a phone/TV provider, a partner, or a business contract. Leave out or 'unknown' to get every route and the question to ask"New value: +"Who charges them (card statement or receipt): the company (direct_web; direct_app in its app), Apple, Google Play, Amazon, Roku, PayPal, a phone or TV provider, a partner or a contract. Omit or 'unknown' for every route and the question to ask. Short words are aliases"
    • changedInput schema / properties / billed_by / enum
      Previous value: -[
      -  "direct_web",
      -  "direct_app",
      -  "apple_app_store",
      -  "google_play",
      -  "amazon",
      -  "roku",
      -  "paypal",
      -  "carrier_or_isp",
      -  "reseller_or_partner",
      -  "sales_contract",
      -  "unknown"
      -]New value: +[
      +  "direct_web",
      +  "direct_app",
      +  "apple_app_store",
      +  "google_play",
      +  "amazon",
      +  "roku",
      +  "paypal",
      +  "carrier_or_isp",
      +  "reseller_or_partner",
      +  "sales_contract",
      +  "unknown",
      +  "apple",
      +  "app_store",
      +  "ios",
      +  "itunes",
      +  "google",
      +  "android",
      +  "play",
      +  "carrier",
      +  "isp",
      +  "phone",
      +  "cable",
      +  "tv_provider",
      +  "partner",
      +  "bundle",
      +  "reseller",
      +  "marketplace",
      +  "web",
      +  "website",
      +  "direct",
      +  "online",
      +  "company",
      +  "app",
      +  "in_app",
      +  "contract",
      +  "sales",
      +  "enterprise",
      +  "invoice"
      +]
    • addedInput schema / properties / monthly_price
      Added value: +{
      +  "description": "USD a month: with renewal_date or months_left, estimates an early termination fee",
      +  "maximum": 100000,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / months_left
      Added value: +{
      +  "description": "Monthly payments left (else from renewal_date)",
      +  "maximum": 120,
      +  "minimum": 0,
      +  "type": "integer"
      +}
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds substantial context: each fact is 'sourced to the vendor's own page with a check date', results are summarized, and it discloses exactly what is logged (vendor names, prices, seats, usage numbers) versus what is not (answer contents, billing sources, IP addresses). The 'they sign in, see any offer, and confirm the final step' line clarifies that no mutation happens on the user's behalf.

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 trigger condition and the sibling routing are front-loaded where they matter most, and the return-value inventory is a useful single dense sentence. The trailing data-retention paragraph is long relative to its decision value and pushes the size toward the upper limit, though every sentence is at least functional.

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?

With eleven parameters, no output schema, and a large result surface, the description compensates by fully inventorying what comes back (routes, steps, notice periods, fees, refunds, export guidance, agent notes) so the agent knows what to expect. Safety is already covered by annotations, and billing/market hints plus the no-cancel-without-consent rule close the remaining gaps.

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 73%, so the schema already carries most parameter meaning. The description reinforces two of eleven params — billed_by ('the name on their card statement or receipt') and renewal_date ('the last safe day to cancel') — but both points largely restate what the schema fields already say, and goal, market, region, contract, start_date, months_left, monthly_price and months_elapsed are never mentioned in the narrative.

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?

The description names a specific verb and artifact ('Returns Stackcut's exit plan') and enumerates exactly what the plan contains: cancellation routes by biller, on-screen steps, access end dates, notice periods, fees, export advice, cheaper alternatives, and sourced citations. It distinguishes itself from the sibling prepare_negotiation by routing retention offers elsewhere, so an agent can separate the two 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?

Trigger conditions are explicit and enumerated ('cancel, unsubscribe from, pause or pay less'), reinforced with concrete user phrasings ('cancel YouTube TV', 'how do I get out of Adobe'). The alternative is named with its selecting condition: 'For a retention offer they hold, use prepare_negotiation.' It also sets the interaction guardrail ('Never cancel for the user without their go-ahead') so the agent knows this tool informs rather than acts.

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.