Skip to main content
Glama
AgentExtract MCP

AgentExtract MCP

extract_clean_markdown

Extracts clean Markdown from any web URL by stripping ads, cookie popups, and navigation clutter, reducing LLM prompt tokens by 70% to 90%.

Instructions

Extracts dense, token-optimized clean Markdown from any web URL. Strips banners, cookie popups, navigation clutter, and ads, saving 70% to 90% of LLM prompt tokens.

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": {
      "url": "<url>"
    },
    "name": "extract_clean_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe absolute URL of the web page to scrape.
apiKeyNoOptional API key. If omitted, uses AGENT_EXTRACT_API_KEY from environment.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

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 must carry the full behavioral burden. It does disclose concrete behavior beyond the name — it strips banners, cookie popups, navigation clutter, and ads, and quantifies token savings at 70-90% — but says nothing about authentication requirements, rate limits, JS rendering, paywall/blocked-page behavior, or what happens on failure.

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 sentences with zero waste: the core action and output format lead, and the token-savings benefit follows as supporting rationale. Nothing is repeated from the schema.

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 two-parameter, fully documented read-style tool with no output schema, the description covers what comes back (clean Markdown) and why it is preferable (token reduction). Remaining gaps — paywalls, JS-only pages, error behavior — are real but not fatal for a simple extraction utility.

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 both url and apiKey are already documented, including the AGENT_EXTRACT_API_KEY fallback. The description adds no syntax, format, or behavioral detail about either parameter, so the baseline of 3 applies.

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 ('Extracts ... clean Markdown from any web URL') plus the output quality (dense, token-optimized). An agent can tell this is a URL-to-Markdown scraper, though it never contrasts itself with the sibling extract_tables, so the boundary between structured table extraction and prose extraction is left to inference.

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 is only implied: 'from any web URL' plus the token-savings claim suggest using it when prompt budget matters, but there is no explicit when-to-use, no when-not-to-use (paywalls, login-gated pages, JS-heavy sites), and no pointer to extract_tables when tabular data is the goal.

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