Extract public web pages as Markdown or HTML through Streamable HTTP without an API key. Anonymous access supports synchronous extract only, limited to 5 requests/minute, 1 concurrent request and 100 MB/day per network address; JavaScript rendering, crawl, search and other advanced capabilities require an API key.
Scored across 1 tool
With a single tool there is no risk of an agent picking the wrong one, so ambiguity is minimal by construction. However, the description overloads 'extract' with sync vs. async, render_js, proxy targeting, headers, and wait_config modes, and references a 'job' tool that isn't present, which muddies what the single tool actually does.
A lone name 'extract' is a clean, simple verb and cannot conflict with anything else, so consistency is technically perfect. There is no verb_noun pattern to evaluate across a set, and the description freely mixes snake_case parameters (render_js, wait_config) with prose, but tool naming itself is unambiguous.
One tool is too few for the surface the description implies: it advertises crawl, map, search, batch, and job-history capabilities plus an async 'job' polling tool, none of which are exposed. Agents must work through a single overloaded entry point for a multi-operation domain.
The domain (web scraping/crawling platform) clearly extends beyond extraction, yet only 'extract' exists. Async mode returns a job ID that no exposed tool can poll, and crawl/map/search/batch operations mentioned in the description are absent, creating dead ends for agents.
Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP headers, and explicit browser wait controls via the wait_config object. Can run synchronously (returns content immediately) or asynchronously (returns a job ID that can be polled with the 'job' tool). Use 'render_js=true' for pages that require JavaScript to load their content; supplying wait_config also enables browser rendering automatically. Omit wait_config or set it to null to keep the adaptive browser settle path; send {} or concrete values to opt into explicit mode. Anonymous use (no API key) is synchronous only, without JavaScript rendering or custom headers other than Accept-Language, and limited to a small per-client rate and daily volume. An API key, sent as the X-Api-Key header, removes these limits and unlocks crawl, map, search, batch and job history: https://geonode.com/pricing?utm_source=mcp-anon&utm_medium=mcp&utm_campaign=keyless-access
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | ||
| extract_request | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so richly: anonymous rate/daily limits, header restrictions (only Accept-Language), sync-only anonymity, API-key unlocks, sync vs async return behavior, and the render_js/wait_config interaction including rejection when ambiguous. These are behavioral traits no structured field provides.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Purpose is front-loaded and each subsequent sentence adds a distinct capability or constraint. It is dense and slightly repetitive around wait_config/render_js interplay, but there is little pure filler given the tool's breadth.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex, many-option extraction tool with no output schema and no annotations, it covers auth tiers, limits, rendering, and async mechanics well. It stops short of describing the returned content structure or metadata fields, which an agent would still need to discover empirically.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Top-level schema description coverage is reported at 0%, so the description must compensate, and it adds real semantics for the tricky cases: wait_config null vs {} opt-in, auto-enabling of render_js, and header forwarding behavior. It is quieter on timeout, proxy type, and formats, which the nested schema happens to document, so it is strong but not exhaustive.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Opens with a precise verb+resource ("Extract content from a web page") and immediately qualifies the scope with supported output formats, JS rendering, proxy targeting, headers, and wait controls. An agent knows exactly what the tool produces and which capability knobs exist without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives actionable conditions: use render_js=true for JS-dependent pages, omit wait_config to keep adaptive settle, send {} for explicit mode, and anonymous use is sync-only. It names the 'job' tool as the polling alternative for async, but does not advise when to prefer sync vs async, leaving that inference to the caller.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
extract
Add one secure layer between your agents and this server.