graph-excel-mcp

read_range

Read-only

Reads a contiguous Excel range from a SharePoint or OneDrive workbook, returning cell values with SHA-256 hashes for safe write validation and optional fill colors or hash-only output.

Instructions

Read one contiguous range (e.g. H60:J60). Each cell comes with sha256: to pass back as expected when writing. fills=true adds each cell's fill color (≤400 cells). hashOnly=true omits the text (just hash + length).

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>",
      "sheet": "<sheet>",
      "range": "<range>"
    },
    "name": "read_range"
  }
}

Input Schema

Name	Required	Description
`file`	Yes	Workbook: SharePoint URL, an alias from ~/.graph-excel/workbooks.json, or "driveId:itemId"
`fills`	No
`range`	Yes
`sheet`	Yes	Worksheet name exactly as listed by resolve
`hashOnly`	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 only declare readOnlyHint and openWorldHint; the description adds genuinely new behavior: each cell carries a sha256 hash to be passed back as `expected` on writes (an optimistic-concurrency contract), and fills=true is capped at ≤400 cells. It stops short of saying what happens when the cap is exceeded or what the returned 'length' represents.

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 short sentences, front-loaded with the core action and immediately followed by the hash contract that governs follow-on writes. Slightly telegraphic phrasing ('Each cell comes with sha256:<hash>') costs a little readability but nothing 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?

With no output schema, the description does the necessary work of sketching the return shape (text, hash, optional fill color) and the hash round-trip contract. For a five-parameter read tool this is nearly complete; only scale limits on the non-fills path and error/truncation behavior are absent.

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 40% — range, fills, and hashOnly have no schema descriptions. The description compensates by defining the range format example and the effect of both boolean flags, adding meaning well beyond the schema for three of five parameters.

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?

Opens with a specific verb+resource ('Read one contiguous range') and gives a concrete range example (H60:J60), so the operation is unambiguous. It doesn't explicitly name a sibling it is distinct from, but 'contiguous' implicitly separates it from multi-range or search operations like find, leaving only mild 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?

Usage conditions for the optional flags are stated ('fills=true adds...', 'hashOnly=true omits the text'), which is real guidance. However there is no explicit when-to-use/when-not guidance relative to siblings like find, resolve, or write_values, and no statement about what to do for non-contiguous ranges.

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

Deploy Server