graph-excel-mcp

append_update

Destructive

Append or replace update text in specific row cells while preserving the original content byte-for-byte, then verify integrity and optionally highlight the changed cells.

Instructions

Write the 「-----update-----」 part of cells in one row (e.g. H/I/J) and keep the original part byte-identical. No separator yet: appends blank line + separator + text. Separator present: mode=replace (default) swaps the update part, mode=append adds after it. Pass expected per column (sha256 from read_range) as the base check. After writing it verifies the original part is intact, then fills fillRange (default the updated columns of that row) with fill (default #FFFF00; null = no fill).

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>",
      "row": "<row>",
      "update": "<update>"
    },
    "name": "append_update"
  }
}

Input Schema

Name	Required	Description
`row`	Yes
`file`	Yes	Workbook: SharePoint URL, an alias from ~/.graph-excel/workbooks.json, or "driveId:itemId"
`fill`	No
`mode`	No
`send`	No	false (default) = dry run: shows what would change. true = write — only after the user approved (or a standing rule allows it)
`sheet`	Yes	Worksheet name exactly as listed by resolve
`update`	Yes	Column letter -> update text, e.g. {"H": "1. ...", "J": "..."}
`expected`	No	Column letter -> exact current text or sha256:<hash>
`fillRange`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.0Nov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, and the description earns credit by explaining exactly what gets mutated: the update part is swapped in replace mode, appended to in append mode, and the original part is preserved byte-identically and re-verified afterward. It also discloses the automatic fill applied after writing. What is missing is what happens when the post-write verification fails.

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?

The core action is front-loaded in the first clause and every sentence carries operational detail, with no filler. The dense shorthand (backticked param names, parenthetical defaults) makes it slightly hard to parse on first read but does not waste space.

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 9-parameter destructive mutation with no output schema, the description covers the write mechanics, conflict checking, and post-write fill adequately. The remaining gap is the return/verification outcome, which an agent would need since no output schema documents it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 56% schema coverage, the description compensates well: it explains mode semantics and the replace default, that `expected` takes a sha256 from read_range as a base check, that `fillRange` defaults to the updated columns of the row, and that `fill` defaults to #FFFF00 with null meaning no fill. That is meaningful guidance well beyond the bare schema types.

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?

The description states a specific verb and resource: write the 「-----update-----」 portion of cells in one row while keeping the original part byte-identical. The marker convention makes it recognizably narrower than the generic write_values sibling, though it never names that sibling to make the boundary explicit.

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?

It gives clear conditional guidance for the two structural cases (no separator yet vs separator present) and defines what mode=replace vs mode=append do. However, it never says when to reach for this tool instead of write_values or set_fill, and the approval/dry-run workflow only appears in the schema's `send` description rather than here.

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

Deploy Server