Skip to main content
Glama

Linkup page fetch

linkup-fetch
Read-only

Fetch a single web page as clean Markdown, with optional JavaScript rendering and schema-based JSON extraction for structured data.

Instructions

Fetch one web page as clean markdown with Linkup (POST /v1/fetch, synchronous).

Price per call: standard 0.001 (no JS) or 0.005 (render_js); pro 0.005 or 0.01; a schema adds 0.001. Returns markdown and favicon always; data with a schema; images with extract_images; rawContent and contentType with include_raw_content. The endpoint is anonymous, reads this one URL only and follows no links. HTTP 400 is returned for binary files other than PDF, unreachable targets, oversize pages, instructions without schema, and failed structured extraction; such calls are not billed.

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": "linkup-fetch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesHTTP or HTTPS URL of an HTML page (up to 20 MB) or PDF (up to 100 MB). No login walls, no LinkedIn (use linkup-search for LinkedIn).
modeNopro has a much higher success rate on hard-to-retrieve pages (anti-bot), at 0.005 or 0.01 per call instead of 0.001 or 0.005. Independent of render_js.standard
schemaNoOptional JSON Schema (root type object) to extract typed JSON from this page into the data field. Fields not found on the page are omitted, even if required. Adds 0.001.
max_charsNoCap on the size of the returned JSON; the markdown (and rawContent) are truncated to fit and _truncated is set.
render_jsNoRender JavaScript before extraction. Use true for single-page apps or when the markdown comes back short or says 'Loading'. Raises the price from 0.001 to 0.005 (standard) or 0.005 to 0.01 (pro).
instructionsNoGlobal extraction rules for schema fill, up to 4000 characters (for example 'public list prices only, in USD'). Requires schema.
extract_imagesNoAlso return the list of images (alt, url). Adds latency.
include_raw_contentNoAlso return rawContent (raw page bytes as text) and contentType. Large.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With readOnlyHint/openWorldHint/destructiveHint already covering the safety profile, the description still adds substantial operational context: per-call pricing tiers, that the endpoint is anonymous, that no links are followed, and that 400-class failures (binary non-PDF, unreachable, oversize, instructions without schema, failed extraction) are not billed. The only meaningful gap is that cost multipliers are stated as flat ranges without tying them to specific parameter combinations in one place.

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?

Purpose is front-loaded in the opening clause, followed by cost, then return shape, then failure modes — a sensible order for an agent. The pricing sentence is dense and partially duplicates the schema's per-parameter price notes, but every remaining sentence (billing on failure, single-URL scope) carries real information.

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 an eight-parameter read tool with no output schema, the description covers what is returned and under which flags, what failures look like, and what is charged — everything an agent needs to call it and interpret the result. Auth posture (anonymous) and scope limits are also stated, leaving no material gap.

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 eight parameters are already documented, including prices for mode, render_js, and schema. The description mostly restates those price points, adding only the linkage between parameters and return fields ('data with a schema', 'images with extract_images', 'rawContent and contentType with include_raw_content'). That is a small increment over a schema that already does the heavy lifting.

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?

The first sentence names a specific verb and resource ('Fetch one web page') and the output form ('clean markdown'), plus the underlying endpoint (POST /v1/fetch, synchronous). It implicitly separates itself from crawlers via 'reads this one URL only and follows no links', but it never names a sibling such as linkup-extract or linkup-search in the description itself, so differentiation from the rest of the catalog is only partial.

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 implied rather than stated: 'reads this one URL only and follows no links' tells the agent this is a single-URL tool, and the HTTP 400 list signals what inputs will fail. There is no explicit 'use this instead of X when Y' routing, and the guidance that does exist for LinkedIn lives in the schema, not the description.

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