SerpKite

Extract pages

extract

Read-onlyIdempotent

Read up to 20 URLs (HTML or PDF) as clean Markdown. With query + highlights, return only the passages most relevant to the query; with summary, a short summary; with output_schema, structured JSON. 1 credit per URL read (+4 summary, +4 output_schema); failed URLs and failed AI steps are free.

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": {
      "urls": "<urls>"
    },
    "name": "extract"
  }
}

Input Schema

Name	Required	Description
`urls`	Yes
`query`	No	What to rank passages against (with highlights)
`prompt`	No	Guides output_schema extraction (what to pick, how to normalise)
`country`	No	Fetch the pages as seen from this country, e.g. de
`summary`	No	Add a 3-6 sentence summary of each page (+4 credits per page)
`timeout`	No	Seconds to wait for the pages; slower ones are reported as failed (not charged)
`highlights`	No	Passages per page ranked against query (0 = full page)
`max_tokens`	No	Cap per page
`output_schema`	No	A JSON Schema: return each page's data as JSON matching it (+4 credits per page)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / country / description

Previous value: -"Fetch through an exit in this country, e.g. de"New value: +"Fetch the pages as seen from this country, e.g. de"

Changed3 schema fields changedOct 24, 2026

addedInput schema / properties / output_schema

Added value: +{
+  "description": "A JSON Schema: return each page's data as JSON matching it (+4 credits per page)",
+  "type": "object"
+}

addedInput schema / properties / prompt

Added value: +{
+  "description": "Guides output_schema extraction (what to pick, how to normalise)",
+  "type": "string"
+}

addedInput schema / properties / summary

Added value: +{
+  "description": "Add a 3-6 sentence summary of each page (+4 credits per page)",
+  "type": "boolean"
+}

First observedOct 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld/destructive=false, so the safety profile is covered. The description adds genuinely new behavior: the credit cost model, that failed URLs and failed AI steps are free, and (via schema framing) that failures are reported rather than thrown. It stops short of describing pagination or the response envelope, which keeps it from a 5.

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?

Three dense sentences, front-loaded with what is read and how much, followed by mode selection and cost. No sentence is filler and the numeric limits/costs are placed where an agent will see them first.

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 9-parameter extraction tool with no output schema, the description covers the core contract (input shapes, limits, billing, failure handling) and the schema carries the rest at 89% coverage. Minor gap: no description of what a result item looks like or how per-URL failures are surfaced in the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 89%, so the baseline is 3; the description earns above that by explaining parameter interactions the schema cannot — notably that highlights is only meaningful against a query, and that output_schema and summary are billed add-ons. It omits any mention of country, prompt, timeout, or max_tokens semantics.

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 a specific verb and resource with a hard scope ('Read up to 20 URLs (HTML or PDF) as clean Markdown') and then enumerates the output modes. An agent can tell this is a fetch-and-convert tool rather than a crawler or search tool 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.

Usage Guidelines4/5

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

Gives explicit conditional routing: 'with query + highlights', 'with summary', 'with output_schema' each produce a different result shape, which tells the agent which parameter combination to pick. It does not, however, contrast itself against the siblings (crawl, webpage, search), leaving that inference to the agent.

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

All SerpKite tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.