Skip to main content
Glama

owa_help_search

Search the app's built-in manual and internal notes to answer how-to, where-is, and feature questions before checking the UI. Use focus to target the correct window.

Instructions

Search this app's own knowledge for how to do something in it -- FIRST for any "how do I", "where is" or "what does X do" question, before poking at the UI. manual is the user-facing recipes answers are written from; internal is notes for whoever BUILDS the app (file paths, code names) -- read one, never repeat it to a volunteer.

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": {
      "query": "<query>"
    },
    "name": "owa_help_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoDefault `auto`: the manual, then internal notes only when the manual has nothing.
focusNoThe window the user is asking about. ALWAYS pass it: another window's recipe names buttons that are not on their screen. Keys that are not the window name: reader = Bible Reader, appDocumentEditor = Document Editor, lwShare = Local Web Share.
limitNo
queryYesWhat the user wants to do, in their words

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.11.15

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does disclose the nature of each corpus (user-facing recipes vs builder notes with file paths and code names) plus an operational constraint about not repeating internal notes to volunteers. It does not describe how answers come back, ranking, or what an empty result looks like, which is a real gap for a retrieval tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both front-loaded with the decision the agent has to make (search first) and then the consequence of the kind choice. No restated parameter definitions, no filler; the backticked enum names are used as shorthand rather than re-explained.

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?

No output schema exists, so the description must convey what comes back; it signals that answers are written from recipes, which tells the agent to expect procedural text. What is still missing is result shape and how the `limit`/empty-result behavior manifests, a modest omission for a search tool.

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 75% and already documents `kind`, `focus` and `query`, so the schema does the heavy lifting. The description still adds meaning the schema lacks: what `manual` and `internal` actually contain and why the distinction matters, which lets the agent reason about the `kind` enum rather than just read it.

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 ("search this app's own knowledge for how to do something in it") and immediately separates the two corpora it can search, `manual` vs `internal`, so an agent knows what content it gets back. It also implicitly distinguishes itself from the UI-poking siblings (owa_click, owa_find_ui) by telling the agent to search first.

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?

Gives an explicit trigger ("FIRST for any 'how do I', 'where is' or 'what does X do' question") and an explicit ordering constraint ("before poking at the UI"), which is the key routing decision against the UI-interaction siblings. It also sets a disclosure rule for the two kinds, so when-to-use is fully determined.

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