graph-excel-mcp

write_values

Destructive

Writes contiguous blocks of cell values to Excel worksheets, checking expected content to skip conflicts and verifying results by reading cells back.

Instructions

Write blocks of cell values. Each block is one contiguous range with a 2D values array (a scalar for one cell). expected (same shape; exact text, sha256:, or null to skip a cell) is the base check: a block whose current content differs is skipped as a conflict, never half-written. After writing, every block is read back and compared (status written-verified / written-mismatch). Values are interpreted like typed input: text that looks like a number/date may be converted — mismatches report it.

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>",
      "writes": "<writes>"
    },
    "name": "write_values"
  }
}

Input Schema

Name	Required	Description
`file`	Yes	Workbook: SharePoint URL, an alias from ~/.graph-excel/workbooks.json, or "driveId:itemId"
`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
`writes`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.0Nov 6, 2026

TDQS

A4/5.0

Behavior5/5

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

Goes well beyond the annotations (destructiveHint=true, openWorldHint=true) by disclosing the failure model: a mismatched `expected` causes the whole block to be skipped, never half-written, and every block is re-read and returned as written-verified or written-mismatch. It also warns that values are coercion-prone ('text that looks like a number/date may be converted'), which is exactly the kind of surprise an agent needs flagged before a destructive write.

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?

Front-loaded with the core action, then the semantics of the two derived concepts (base check, read-back). Dense but every clause carries information; the heavy use of parentheticals and semicolons makes it slightly harder to scan than it could be, but nothing is redundant.

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 destructive multi-block write with no output schema, the description covers atomicity, conflict handling, verification results, and type coercion. It omits practical constraints an agent may need, such as whether blocks may overlap, ordering of application, or size limits, which keeps it short of full completeness.

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 75%, but the undocumented parts are precisely the nested `range`, `values`, and `expected` fields, and the description compensates: `values` is a 2D array (scalar for one cell), `expected` must match its shape and accepts exact text, sha256:<hash>, or null to skip a cell. That is real meaning beyond the bare schema; only `range` syntax (A1 notation?) remains unexplained.

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: 'Write blocks of cell values', and immediately defines a block as one contiguous range with a 2D values array. It is clear what the operation does, but it never names or contrasts itself with the plausible siblings append_update or append_rows, so an agent must infer the boundary itself.

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 context is implied rather than stated: the read-back/conflict behavior hints at bulk exact-write scenarios, and the approval precondition lives only in the `send` schema description, not here. There is no explicit 'use this instead of append_update when...' guidance even though several siblings touch cell contents.

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

Deploy Server