Skip to main content
Glama
Sign In
adhistory-mcp

adhistory-mcp

by OBrandon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Table in an image to data

image_tables
Read-onlyIdempotent

Extract table data from image URLs via OCR and return rows, columns, confidence scores, and CSV/Excel links for spreadsheet use.

Instructions

Read tables out of pictures (screenshots, photos of printed tables; PNG, JPG, WEBP, BMP, TIFF) at public URLs using OCR. Each item is one table: rows and columns as text, the OCR confidence, plus CSV and Excel links. Honest limit: OCR can misread small or blurry text, so check numbers that matter. Cost: $2.00 per 1,000 tables ($0.002 each) on the user's Apify account. Latency: usually 10-40 s.

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": {
      "image_urls": "<image_urls>"
    },
    "name": "image_tables"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_urlsYesDirect public links to table images (https://...).
max_tablesNoStop after this many tables.
first_row_is_headerNoUse the first row as column names.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), the description discloses pricing ($0.002 per table, billed to the user's Apify account), expected latency (10-40 s), and an honest accuracy limit for small or blurry text. These are exactly the operational details an agent needs before committing a paid, slow call.

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 paragraph is front-loaded with purpose and input types, then cost, then latency, with no filler sentences. The one item that does not earn full place is the return-shape sentence ("rows and columns as text... CSV and Excel links"), which duplicates what the output schema already declares.

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

Completeness5/5

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

For a paid, slow, probabilistic OCR tool, the definition covers inputs, formats, limits, accuracy caveats, cost, and latency, and an output schema handles return values. An agent has everything needed to decide whether to call it and what to expect.

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 description coverage is 100%, so all three parameters (image_urls, max_tables, first_row_is_header) are already documented inline, including the 20-item cap. The description repeats the public-URL requirement but adds no new per-parameter meaning or format guidance beyond the schema, so the baseline applies.

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?

The description uses a concrete verb and resource ("Read tables out of pictures") and immediately scopes it with example inputs (screenshots, photos of printed tables) plus supported formats (PNG, JPG, WEBP, BMP, TIFF). That wording distinguishes it from a PDF-oriented sibling such as pdf_tables without needing to name it.

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

Usage Guidelines4/5

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

It states the precondition clearly (tables must be reachable at public URLs) and lists input types that qualify. It stops short of explicitly naming alternatives or when-not-to-use cases (e.g. use pdf_tables for PDFs), so the agent must infer the routing.

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