Skip to main content
Glama

owa_guide_start

Starts an in-app walkthrough that guides users through a task step by step with on-screen numbered cards and highlighted controls, either showing steps or performing them in demo mode.

Instructions

Walk the user through a task IN THE APP WINDOW: a numbered card in the corner, each step's control ringed in red; the user presses Next or just does the step. The default show presses NOTHING, so start it when they ask to be walked through. Pass manualId (a recipe id from owa_help_search), a built-in page demoId, or your own steps: each ONE plain instruction for a volunteer, its find the exact words on the control it means. A manualId is for show mode only; a custom demo must pass exact live steps. mode: "demo" adds Do it, which performs one step per press: a click, a type/slider change with its value, a hover that reveals another control, a rightClick menu item, or a press shortcut. A user who asked you to do it FOR them has said yes to the demo already. Never demo a step that changes what the congregation sees without asking first. Answers as owa_guide_status does.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "owa_guide_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
findNoThe exact words on the control the task is about: with a manualId the step naming it starts, that control first.
modeNo
pageNoPart of the window URL, e.g. "reader.html"; default the main window.
stepsNo
titleNo
topicNoThe user's task in their own words; with a manualId, start at the matching recipe step.
demoIdNoA built-in page demo id selected in the app; no model-written steps needed.
manualIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.11.15

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does most of it: it discloses that `show` is non-mutating, that `demo` performs one real action per press (click, type/slider value, hover, rightClick, shortcut), and warns about visibility-affecting actions. It is slightly light on what the guide returns beyond the pointer to `owa_guide_status`, and on what happens if a step's `find` never matches.

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?

Front-loaded with what the tool does and how the user experiences it, then moves into mode/parameter rules. It is dense and backtick-heavy with several clauses per sentence, but almost every sentence carries decision-relevant information, so little is wasted.

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 8-parameter, zero-required, unannotated tool with no output schema, the description covers the mode choice, all three step sources, the risk guardrail, and the return behavior by reference. Gaps are minor: `title` and `page` handling are only in the schema, and failure behavior for unmatched `find` or `demoId` is unstated.

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 only 50%, but the description compensates for the important parameters: `manualId` is show-mode only, `demoId` is a built-in page demo needing no model-written steps, and `steps` must be one plain instruction per step with `find` matching the exact words on the control. `page`, `title`, and `topic` are left to their schema descriptions, so it is not exhaustive.

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 — walking the user through a task inside the app window with a numbered card and red-ringed controls — and makes the output form concrete. It also distinguishes itself from siblings by noting that recipe ids come from `owa_help_search` and that answers come back like `owa_guide_status`.

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?

Explicitly says when to start it ('start it when they ask to be walked through'), why mode `show` is the safe default ('presses NOTHING'), and that a user who asked you to do the task FOR them has already consented to demo mode. It also gives a hard exclusion — never demo a step that changes what the congregation sees without asking first — plus the manualId-vs-custom-steps rule.

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