Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL.
Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | URLs to read. Batch multiple URLs in one call. | |
| maxCharacters | No | Maximum characters to extract per page (default: 3000) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful context about returning clean markdown and metadata, and supporting batching. However, it claims 'full content' while the schema includes a maxCharacters default of 3000, and the description does not disclose that pages are truncated unless the limit is increased, which is a significant gap in behavioral transparency.
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?
The description is three short sentences, each adding value: the core function, usage guidance, and return expectation. It is front-loaded with the most important information and avoids any fluff or repetition.
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 simple read tool with two parameters and strong annotations, the description is mostly complete: it states the input (URLs), output (text and metadata), and when to use it. The only notable omission is the character limit caveat, which prevents a perfect completeness score.
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?
The schema already provides descriptions for both parameters (urls and maxCharacters), covering 100% of the parameters. The description contributes little beyond repeating the batching capability already in the schema, so it does not add meaningful extra meaning beyond the structured data.
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?
The description clearly states the tool reads a webpage's full content as clean markdown, with an explicit verb and resource. It also distinguishes from the sibling tool web_search_exa by specifying its use case: after search when highlights are insufficient or for reading any URL.
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?
The description explicitly says to use this tool after web_search_exa when highlights are insufficient, and it highlights best uses (extracting full content from known URLs, batching multiple URLs). This provides clear when-to-use guidance and names the alternative, leaving no ambiguity about when to choose this tool over the sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
web_search_exa is for discovering relevant pages via query, while web_fetch_exa retrieves full content from known URLs. The descriptions explicitly cross-reference each other, leaving no ambiguity about which tool to use.
Both tools follow a consistent web_<action>_exa pattern. The verb-first structure clearly indicates the operation, and the shared suffix signals the server's branding.
Two tools is slightly below the typical 3-15 range, but each tool earns its place and together they cover the core search-and-fetch workflow of the server. The minimal surface feels reasonable for this narrow domain.
The server provides the essential lifecycle for web research: search to discover relevant pages and fetch to read full content. There are no obvious missing operations for the stated purpose.
