Skip to main content
Glama

owa_drag

Drag labeled controls onto targets to attach, replace, reorder, or play items using on, before, or after placement. Check accepted results and verify unverified drops against the list.

Instructions

Drag one control onto another, both found by their labels -- a Documents row into a presenting flow, a slide onto another slide, a background onto a slide card. place is where on the target: on (default) is what dropping on it means in the app (attach, replace, play); before / after put it at that position in a list. The answer says whether anything took the drop (accepted); on unverified check the list before saying it worked. Same refusals as owa_click.

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "owa_drag"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesThe label on the thing to drop it on
fromYesThe label on the thing to drag
pageNoPart of the window URL, e.g. "reader.html"; default the main window.
placeNoon (default) drops onto the control; before / after are a row's reorder bands, Ctrl held -- after lands on the next row's top band, which is how this app's rows read it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2026.11.15

TDQS

A4.3/5.0
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 meaningful work: it discloses that the response reports whether anything took the drop (`accepted`), that `unverified` means the outcome must be confirmed before claiming success, and that it shares owa_click's refusal behavior. What it does not cover is the failure path when a label matches nothing, or whether the drag auto-scrolls — the residual gaps keep it at 4 rather than 5.

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?

Three dense sentences, front-loaded with purpose, then placement semantics, then the result contract — no preamble or filler. Some phrasing is terse to the point of needing a second read (e.g. 'is what dropping on it means in the app'), which slightly undercuts first-pass legibility.

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 a four-parameter mutation tool with no annotations and no output schema, the description covers the essentials: intent, target resolution by label, placement semantics, and the shape of the return (`accepted` vs `unverified`) plus a delegation to owa_click for refusal cases. It falls short of complete only in not describing behavior when a label fails to resolve.

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 exceeds that by explaining what `place` actually means operationally — that `on` defers to the app's own drop behavior (attach, replace, play) whereas `before`/`after` map to list positions. That framing is not recoverable from the enum alone and materially affects how an agent chooses a value.

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 opens with a precise verb+resource pair ('Drag one control onto another, both found by their labels') and immediately grounds it in three concrete scenarios (Documents row into a presenting flow, slide onto slide, background onto a slide card). An agent knows exactly what operation this performs and how targets are located, which clearly separates it from click- and lookup-style siblings.

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?

It gives real selection logic for the `place` parameter: `on` for app-defined drop semantics, `before`/`after` for list repositioning. What is absent is any explicit statement of when NOT to use this tool, or how to choose between it and the similarly named `drag` sibling, which is left to inference.

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