Skip to main content
Glama
Sign In

Conecto

by chat.conecto
OverviewDiscussionsAdmin

See the pages of a scan

documents_page_images
Read-onlyIdempotent

The pages of a scanned PDF or a photo of a document (a receipt, a letter, a signed form) as images for you to read yourself, with any text the PDF already has. Up to 10 pages a call; ask for later pages with first_page. files_ocr turns a scan's printed words into text instead ($0.005 a page); for PDFs with text, documents_read_pdf is free. Costs $0.005 per call; nothing if it fails.

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_id": "<file_id>"
    },
    "name": "documents_page_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_idYesA file in the store (files_upload or files_list give its file_id).
last_pageNo
first_pageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavioral context: a 10-page cap per call, pagination via first_page, a $0.005 per-call charge, and no charge on failure. It doesn't mention image resolution/format or total page count, which are the only notable gaps.

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-loads what the tool returns before mentioning cost and alternatives; parenthetical examples (receipt, letter, signed form) are load-bearing for tool selection. Slightly dense with semicolons and a repeated price figure, 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 correctly carries the burden of explaining what comes back (page images plus embedded text) and how paging works. Only the last_page parameter and any limits on total page count are left uncovered.

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 only 33% — file_id is documented in the schema, but first_page and last_page have no descriptions there. The description explains how to page forward with first_page and implies the 10-page batch size, but never explains last_page or that ranges are inclusive, so it only partially compensates.

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

Purpose5/5

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

States a specific verb and resource — the pages of a scanned PDF or document photo delivered as images — plus the crucial detail that existing PDF text comes along. It explicitly distinguishes itself from files_ocr and documents_read_pdf, so an agent can pick between them without opening other schemas.

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

Usage Guidelines5/5

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

Gives concrete when-to-use routing: use files_ocr to turn a scan's printed words into text, use documents_read_pdf for PDFs that already have text (and it's free), use this when you need to see the page yourself. Alternatives and their costs are named inline.

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

All Conecto toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources