Skip to main content
Glama

Tavily (Unofficial)

Extract

extract
Read-onlyIdempotent

Extract clean article text from one or more URLs via Tavily: strips boilerplate/navigation and returns up to 20,000 chars of readable content per page. Accepts a single URL string or an array. Ideal for feeding source pages into an LLM.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "urls": "https://www.example.com/article"
    },
    "name": "extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsYesA single URL string, or an array of URL strings, to extract clean text from.
_apiKeyNoOptional, your own Tavily API key for higher limits; omit to use the shared Pipeworx key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / _apiKey / description
      Previous value: -"Optional — your own Tavily API key for higher limits; omit to use the shared Pipeworx key."New value: +"Optional, your own Tavily API key for higher limits; omit to use the shared Pipeworx key."
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "urls": "https://www.example.com/article"
      +  },
      +  {
      +    "urls": [
      +      "https://www.example.com/article1",
      +      "https://www.example.com/article2"
      +    ]
      +  }
      +]
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: boilerplate/navigation is stripped, output is capped at 20,000 chars per page, and the call hits an external service (Tavily). It stops short of saying what happens when a batch partially fails or whether results are per-URL keyed.

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, no filler, with the core action and output characteristics front-loaded before the use-case hint. Each clause carries information an agent cannot get from the structured fields alone.

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?

With no output schema, the description correctly carries the burden of describing the return value (clean readable text, per-page 20k cap), which is the main thing an agent needs. Minor gaps remain around batch failure behavior and result ordering for multi-URL calls, but nothing essential for correct invocation is missing.

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 coverage is 100% and the schema already documents the string-or-array polymorphism and the optional _apiKey for higher limits, so the schema does the heavy lifting. The description restates the single-vs-array acceptance without adding format, validation, or ordering semantics. Baseline 3 applies.

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 ('Extract clean article text from one or more URLs'), names the backend (Tavily), and describes the transformation ('strips boilerplate/navigation') plus the output bound ('up to 20,000 chars of readable content per page'). This is enough for an agent to distinguish it from the research/entity siblings 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 Guidelines3/5

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

Provides an implied use case ('Ideal for feeding source pages into an LLM') but no explicit when-not conditions, no prerequisites, and no named alternatives among the many research-oriented siblings. An agent gets a hint about context but must infer when this beats deep_research or entity_profile.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.