graph-excel-mcp

find

Read-only

Searches cell text across every sheet or one sheet in an Excel workbook by substring or JavaScript regex, returning each hit’s sheet, address, preview, and SHA-256 hash.

Instructions

Search cell text across every sheet (or one sheet): case-insensitive substring by default, regex=true for a JavaScript regular expression. Returns sheet, address, a preview and the sha256 hash per hit (≤ limit, default 50, max 500).

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": {
      "file": "<file>",
      "text": "<text>"
    },
    "name": "find"
  }
}

Input Schema

Name	Required	Description
`file`	Yes	Workbook: SharePoint URL, an alias from ~/.graph-excel/workbooks.json, or "driveId:itemId"
`text`	Yes
`limit`	No
`regex`	No
`sheet`	No	Worksheet name exactly as listed by resolve
`matchCase`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.0Nov 6, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavior: default case-insensitive matching, JavaScript regex dialect, the per-hit return fields (sheet, address, preview, sha256 hash), and the limit default/maximum. The gap is that matchCase is never explained even though the description says matching is case-insensitive 'by default', leaving the override unstated.

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?

A single dense sentence with the scope, matching semantics, and return shape front-loaded in that order. Every clause carries information; nothing is padding.

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?

With no output schema, the description usefully enumerates the returned fields and the cap on hits, which is what an agent needs to plan around results. Remaining omissions are minor but real: matchCase semantics and what happens when hits exceed the limit.

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 coverage is only 33% (only file and sheet documented), so the description has to carry weight — and it does explain regex semantics and limit bounds. But text is left unqualified (whole cell? substring? trimmed?), and matchCase, a boolean whose meaning is precisely the thing 'case-insensitive by default' gestures at, is never defined.

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?

States a specific verb and resource ('Search cell text') plus its scope ('across every sheet (or one `sheet`)'), which implicitly separates it from read_range/write_values siblings. It does not name an alternative tool explicitly, so it stops short of full sibling differentiation.

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 description distinguishes its two search modes (plain substring by default vs regex=true) which is useful mode-selection guidance. However it never says when to use this tool rather than read_range, or when not to use it (e.g. large workbooks, structural searches), so usage is only implied.

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

Deploy Server