AgentGate

by app.railway.up.agentgate-production-15b2

Extract Webpage Content

extract_url_content

Read-onlyIdempotent

Fetches and extracts clean text or raw HTML content from any public HTTP/HTTPS webpage URL via the AgentGate M2M web extraction gateway. Use this tool when an AI agent needs to read, scrape, or summarize external web pages.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	The full HTTP or HTTPS URL of the target webpage to extract content from (e.g., 'https://example.com/article').
`max_length`	No	Maximum number of characters to return from the extracted webpage content. Defaults to 5000 characters.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 19, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / max_length

Added value: +{
+  "default": 5000,
+  "description": "Maximum number of characters to return from the extracted webpage content. Defaults to 5000 characters.",
+  "maximum": 50000,
+  "minimum": 100,
+  "type": "integer"
+}

changedInput schema / properties / url / description

Previous value: -"Target URL to extract"New value: +"The full HTTP or HTTPS URL of the target webpage to extract content from (e.g., 'https://example.com/article')."

addedInput schema / properties / url / format
```
Added value: +"uri"
```

First observedOct 19, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, covering the safety profile. The description adds useful scoping ('public' URLs, routed via the AgentGate gateway), but says nothing about failure modes, rate limits, paywall/auth-walled pages, or what 'clean' text extraction actually strips.

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, zero padding, with the action and scope front-loaded before the usage clause. Nothing repeats the title or schema verbatim without adding information.

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?

There is no output schema, so the description does carry some burden for return values; it partially addresses this by naming clean text vs raw HTML. Combined with 100% schema coverage and full annotations, an agent has enough to call it correctly, though truncation behavior tied to max_length is left implicit.

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 max_length (with default 5000, max 50000) are fully documented in the schema. The description adds no parameter-level meaning and introduces mild confusion by mentioning 'raw HTML' output when no parameter selects an output format.

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 specific verbs (fetches, extracts) and a concrete resource (clean text or raw HTML from an HTTP/HTTPS webpage URL). The sibling tools all concern wallets and gateway health, so there is no ambiguity about which tool to pick for web content retrieval.

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?

Explicitly says when to use it: 'when an AI agent needs to read, scrape, or summarize external web pages.' No alternative tool is named, but the sibling set contains no competing extraction tool, so no exclusion is needed.

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

All AgentGate tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?