Scrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | URLs to scrape (max 10) | |
| format | No | Output format: markdown (default) or text | markdown |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses parallel processing and browser rendering for blocked sites, which are useful behavioral traits. However, it omits potential limitations such as rate limits, errors on inaccessible pages, or the size of returned content, leaving some operational expectations unspecified.
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?
Two efficient sentences with zero filler. The first sentence front-loads the action and purpose, while the second adds a distinctive capability. Every word contributes value.
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 relatively simple tool with fully described parameters, the description adequately explains the tool's purpose, output format, and unique ability to handle blocked sites. It lacks only an explicit tie-in to the sibling tool 'scrape_url' and more detail on failure behavior, but these are minor gaps given the simplicity.
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?
Schema coverage is 100%; both 'urls' and 'format' have descriptions. The text's mention of 'multiple webpages' and 'Markdown format' aligns with these parameters but adds no new semantic detail beyond what the schema already provides. The baseline of 3 applies.
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 states a specific verb ('Scrapes'), a resource ('multiple webpages'), and a distinctive feature ('in parallel') that sets it apart from the sibling tool 'scrape_url' which likely handles single URLs. It also clarifies the output format ('AI-readable Markdown') and a key capability ('access blocked sites through browser rendering').
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 implies usage for multiple URLs and for sites that may be blocked, but it does not explicitly mention when to avoid using this tool or point to alternatives like 'scrape_url' for single pages. While context is clear, no direct comparison or exclusions are provided.
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.
get_billing and get_usage overlap somewhat in describing plan/credit information, but their distinct focus on billing details vs. usage/credits keeps them separable. scrape_url and scrape_urls are clearly differentiated by singular vs. plural operation. scraper_server_status is entirely distinct. Overall, the tools are mostly distinct with only mild ambiguity between billing and usage.
Most tools follow a verb_noun pattern (get_billing, get_usage, scrape_url, scrape_urls), but scraper_server_status deviates as a noun phrase. This mixed convention is still readable and predictable, but not fully consistent.
With 5 tools, the server is well-scoped for a scraping API. It covers single/batch scraping, server status, billing, and usage without unnecessary bloat, making the count appropriate for its purpose.
The tool surface covers the core lifecycle of a scraping service: scraping (single and multiple), health monitoring, and account management (billing/usage). Minor gaps exist, such as lack of detail on plan management or job cancellation, but these are not critical for the primary use case.