Skip to main content
Glama

web_fetch

Fetch and read full content from any URL, including bot-protected sites and package registries. Supports pagination with cursors for large documents.

Instructions

Fetch and read content from a URL via EnriProxy's multi-tier fetch service.

When to use:

  • When you need to read the full content of a webpage.

  • When you need to access documentation, articles, or code files.

  • When simpler fetch methods fail due to anti-bot protection.

Features:

  • Package registry API detection (npm, PyPI)

  • Raw file fetch (GitHub raw, HuggingFace)

  • Robust fetching for static, dynamic, and bot-protected sites (best-effort)

  • Automatic fallback across multiple retrieval strategies (details intentionally not exposed)

Notes:

  • Provide the full URL including protocol (https://).

  • Content is limited by the max_chars parameter (default: 200000).

  • If the result is truncated and includes a cursor, call web_fetch again with cursor + offset + limit to read more without re-fetching.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoFull URL to fetch (http:// or https://).
cursorNoOpaque cursor returned by a previous `web_fetch` call for pagination.
promptNoOptional hint describing what you want to extract (the tool returns fetched content; it does not generate an AI summary).
max_charsNoMaximum content length (default: 200000).
offsetNoCursor read offset in characters (default: 0).
limitNoCursor read limit in characters (default: max_chars).
Behavior4/5

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

With no annotations, the description covers important behaviors: package registry detection, raw file fetch, automatic fallback, and content truncation with cursor pagination. It could be more explicit about error handling or response format.

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?

The description is well-organized with sections and bullet points, providing necessary detail without redundancy. Every sentence adds value, and it is front-loaded with the core purpose.

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?

Given six parameters and no output schema, the description covers purpose, usage, parameters, limitations (max_chars, cursor), and features. Missing explicit return format (e.g., raw HTML, text) is a minor gap.

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?

All six parameters have clear descriptions in the schema (100% coverage). The description adds value by explaining the 'prompt' parameter's non-AI-summary nature and cursor usage, going beyond the schema.

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?

The description clearly states the tool fetches and reads content from a URL using a multi-tier service. It distinguishes itself from the sibling tool 'web_search' by focusing on fetching specific URLs rather than searching.

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?

The 'When to use' section provides explicit scenarios, such as reading webpage content or accessing documentation. However, it lacks explicit 'when not to use' or direct alternatives to other tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Bedolla/EnriWeb'

If you have feedback or need assistance with the MCP directory API, please join our Discord server