Skip to main content
Glama

excel_read

Read Excel spreadsheet data with AI agents to extract cell values, sheet contents, and workbook information on macOS.

Instructions

Read data from an Excel spreadsheet

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • server.js:82-86 (registration)
    Tool registration loop where 'excel_read' is registered with the MCP server using server.tool(). All tools share the same stub handler.
    for (const [name, desc] of TOOLS) {
      server.tool(name, desc, {}, async () => ({
        content: [{ type: "text", text: "This is an inspection stub. Install Pilot MCP on macOS: npx -y local-mcp@latest setup" }],
      }));
    }
  • Tool definition in TOOLS array - 'excel_read' is declared with its description 'Read data from an Excel spreadsheet'
    ["excel_read", "Read data from an Excel spreadsheet"],
  • server.js:82-86 (handler)
    Handler function for excel_read (shared stub handler). Returns a stub message indicating this is an inspection stub and the real server is a native macOS binary.
    for (const [name, desc] of TOOLS) {
      server.tool(name, desc, {}, async () => ({
        content: [{ type: "text", text: "This is an inspection stub. Install Pilot MCP on macOS: npx -y local-mcp@latest setup" }],
      }));
    }
Behavior2/5

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

No annotations provided, so description carries full burden. Fails to disclose return format, whether it reads the entire sheet or requires prior selection, or how it handles multiple sheets. 'Read' implies read-only, but no explicit safety confirmation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is not verbose, but given the ambiguity of a zero-parameter read operation, the description is insufficiently sized. Front-loaded but incomplete.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero parameters, no annotations, and no output schema, the description fails to explain how the tool identifies which spreadsheet to read or what data structure it returns. Critical operational gaps remain.

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?

Input schema contains zero parameters. Per calibration rules, 0 params equals baseline score of 4.

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

Purpose3/5

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

States the basic verb (Read) and resource (Excel spreadsheet) but lacks specificity on scope (which spreadsheet? what range? all data?). Does not differentiate from sibling tools like excel_write_cell or ppt_read.

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

Usage Guidelines2/5

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

Provides no guidance on when to use this versus excel_write_cell or excel_create. No mention of prerequisites like file selection or open documents.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lanchuske/local-mcp-releases'

If you have feedback or need assistance with the MCP directory API, please join our Discord server