Skip to main content
Glama

read_document

Read local PDFs, Office files, HTML, email, and images as clean text, including scans and complex tables, while flagging uncertain content for review.

Instructions

Read a local PDF, Word, PowerPoint, Excel, HTML, email or image file as clean text. Handles scans and complex tables, and marks anything uncertain. Prefer this over reading such files directly.

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": {
      "path": "<path>"
    },
    "name": "read_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose meaningful behavior beyond the schema: OCR of scans, complex-table handling, and marking of uncertain output ('marks anything uncertain'), which tells the agent results may be imperfect. It omits limits that matter for a file-reading tool — path type (absolute vs relative), size/page caps, permission requirements, and whether remote URLs are accepted.

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?

Two tight sentences: capability first, then scope of robustness, then the preference cue. No repetition of the title, no filler, and the most decision-relevant information leads.

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 one-parameter tool with an output schema (so return values need not be explained) and no annotations, this covers formats, robustness, and output quality tolerances well. The remaining gap is path semantics and any size/format constraints, which is modest given the tool's simplicity.

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 0%: the single 'path' parameter is documented only as 'Path'. The description partially compensates by establishing that the path points to a local file and by listing the accepted file types. It still leaves the critical path syntax (absolute vs relative, allowed roots) unspecified.

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 (read) and resource (local file) and enumerates the supported formats (PDF, Word, PowerPoint, Excel, HTML, email, image) plus the output form ('clean text'). It does not differentiate from the siblings read_pages or export_table, so an agent cannot tell from this text alone when document-level reading beats page-level or table export.

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?

'Prefer this over reading such files directly' gives a soft preference against native/manual reading, which is useful context. It gives no guidance relative to the sibling tools (read_pages, export_table), no exclusions, and no prerequisites, so the when-to-use signal 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

Other Tools