Skip to main content
Glama

Add a scenario

add_scenario
Destructive

Add a scenario to an app, in the team's words: a title, what a user does (description) and what must be seen (expects, one sentence each — every check answers each of them, and the answer returns them as they were understood). daily: true (default) puts it in every check of the app; daily: false keeps it for the checks that name it (start_check scenarios). run_now also starts a check of only it, now. If a scenario the check found is really a different one, pass its scenario_id as replaces. For a Shopify app on several stores, all_stores: true adds it on every store of that app (a store connected later gets the app's scenarios too). critical: true walks it on every check, whatever changed — for what must never break; tell the person what it adds per check.

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": {
      "app_id": "<app_id>",
      "title": "<title>"
    },
    "name": "add_scenario"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamNoAct in another of your teams, by its name or id (whoami lists them). Omitted: the key's own team
dailyNotrue (default): checked by every check of the app. false: only when a check names it
loginNoThe login it walks with, by label (list_apps test_accounts): "default", a named test account, or the app's session sign-in. Left out: the app's default. A login that is gone by the time of a check reports the scenario not checked, never walked as someone else
titleYesWhat the scenario is, as a person would name it, e.g. 'Block a country'
app_idYesApp id from list_apps or create_app
expectsNoWhat must be SEEN for this to count as working, one sentence each, in words the product itself shows — e.g. ["The heading reads «Account settings».", "The page has no «Delete workspace» section."]. Start each with a capital letter. The check answers every one with a step: seen, shows otherwise, or not seen
run_nowNoAlso start a check of the app now that covers it (spends the team's balance)
criticalNotrue: walked on every check — every deploy, preview and daily check — even when nothing near it changed; the answer says what it adds to each check's price. false: walked when something near it changes
replacesNoscenario_id of a scenario the check found that is really this one; it is retired
all_storesNoFor a Shopify app on several stores: add it on every store of that app, not only this one
descriptionNoWhat a user does, in order, e.g. 'Add Germany in Block Countries, then open the store as a German visitor.' What must be seen goes in expects

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / description / description
      Previous value: -"What a user does and what should happen, e.g. 'Add Germany in Block Countries; a German visitor sees the block page'"New value: +"What a user does, in order, e.g. 'Add Germany in Block Countries, then open the store as a German visitor.' What must be seen goes in expects"
    • addedInput schema / properties / expects
      Added value: +{
      +  "description": "What must be SEEN for this to count as working, one sentence each, in words the product itself shows — e.g. [\"The heading reads «Account settings».\", \"The page has no «Delete workspace» section.\"]. Start each with a capital letter. The check answers every one with a step: seen, shows otherwise, or not seen",
      +  "items": {
      +    "maxLength": 200,
      +    "minLength": 8,
      +    "type": "string"
      +  },
      +  "maxItems": 12,
      +  "minItems": 1,
      +  "type": "array"
      +}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the destructiveHint/openWorldHint annotations: run_now spends the team's balance, critical adds a stated per-check price and tells the person what it adds, replaces retires the prior scenario, all_stores propagates to stores connected later, and a vanished login reports the scenario as not checked rather than walking as someone else. These are the operational side effects an agent needs before calling a destructive write.

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 and the definition of a scenario are front-loaded, and each following clause maps to a real parameter decision rather than restating the schema. It is a dense run-on paragraph, though — semicolons chain several distinct ideas that would scan faster as a short list.

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 an 11-parameter destructive, open-world write with no output schema, the description covers costs, retirement of replaced scenarios, cross-store propagation and login failure behavior. It never says what the call returns (e.g. the new scenario_id), which is the one gap an agent must infer from siblings like list_scenarios.

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 coverage is 100%, so the baseline is 3, but the description still adds meaning: it explains the daily/critical trade-off in terms of which checks run, clarifies that expects is one sentence per assertion answered as seen/shows otherwise/not seen, and frames description as the user's steps versus expects as the verification. Only the team parameter is left entirely to the schema.

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?

Opens with a specific verb and resource ("Add a scenario to an app") and immediately defines what a scenario consists of — title, description, expects — which lets an agent distinguish it from update_scenario and remove_scenario 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 Guidelines4/5

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

Gives conditional guidance for the main switches: daily true vs false, run_now for an immediate one-off check, replaces when a found scenario is really this one, all_stores for multi-store Shopify apps, and critical for must-never-break paths. It never explicitly contrasts against update_scenario or list_scenarios, so the create-vs-modify boundary is left to the tool name.

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.