Skip to main content
Glama

ie_grid

Extract tabular grid data from legacy IE pages as structured headers and rows, auto-selecting the table with the most multi-cell rows or a specified table_id.

Instructions

Extract a tabular grid as structured rows. Auto-picks the table with the most multi-cell rows (or pass table_id). Returns headers + rows (header-keyed dicts when the header row is detected/given). App-agnostic.

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": "ie_grid"
  }
}

Input Schema

NameRequiredDescriptionDefault
frameNoframe/path holding the grid (e.g. '3/0')
limitNomax rows (default 500)
targetNoWhere to act: omit it for the session's IE driver; hwnd:<n> acts over COM on the window <n> (a modal dialog's hwnd from a NOTICE or ie_windows), tab:<n> on an attached tab. Over COM, DOM access is script, input is synthetic (script events and a timer click, not mouse or keyboard input; keys are posted window messages) and only id, name, tag, class, link_text and (documentMode 8+) css locators work.
headersNoexplicit column names (optional)
table_idNospecific table element id (optional)
out_limitNomax output chars (default 12000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.3/5.0
Behavior2/5

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

With no annotations, the description must carry the full behavioral burden. It does disclose the auto-selection heuristic ('table with the most multi-cell rows') and the output shaping rule for header-keyed dicts, but says nothing about failure behavior when no table exists, whether the extraction is non-mutating, or how frames/targets affect results beyond what the schema already says.

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?

Four short, front-loaded sentences with no padding; the auto-pick rule and return shape arrive early. 'App-agnostic' is the only near-filler phrase, though it carries mild signal about applicability.

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?

Six optional parameters, no output schema, and the description covers the two most consequential behaviors: how the table is chosen and how rows are shaped. Missing are failure/empty-result behavior and any note on how out_limit truncation interacts with header detection.

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 100%, so every parameter is already documented. The description only echoes table_id and headers in passing and adds no syntax, precedence, or edge-case meaning (e.g. what happens when headers conflict with a detected header row).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Extract a tabular grid as structured rows') and states the returned shape, which distinguishes it from raw-markup siblings like ie_html or ie_get. It never explicitly names an alternative tool, so differentiation is inferential rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

The parenthetical '(or pass table_id)' gives a usage choice between auto-pick and explicit targeting, which is useful. There is no when-to-use/when-not-to-use framing against ie_html or ie_get, and no guidance on what to do when the page has no usable table.

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