read_pageRead one known web page as clean Markdown without raw HTML noise.
Use this for documentation, articles, and product pages when the URL is already known. For an unfamiliar site, use map_site first to choose useful URLs instead of crawling every page.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute HTTP(S) URL of documentation, an article, or a product page to read without raw HTML noise |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds useful behavioral context beyond annotations by specifying the output is clean Markdown with raw HTML noise removed and clarifying that the tool reads exactly one known page.
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 sentences, no filler. The core behavior is front-loaded in the first sentence, and the second sentence gives a clear usage boundary. Every word earns its place.
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 single-parameter, read-only tool with 100% schema coverage and no output schema, the description fully equips an agent to select and invoke it. It states the input, the expected output format, and the primary alternative for unfamiliar URLs.
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 description coverage is 100% and the single url parameter is already well documented with type, minimum length, and intended URL scheme. The description adds no new parameter-specific syntax or constraints beyond the schema, so the baseline 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 and resource: 'Read one known web page as clean Markdown.' It differentiates from siblings by emphasizing a single known URL rather than crawling or searching, and by naming the output format (Markdown).
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?
It explicitly says when to use the tool — for documentation, articles, and product pages when the URL is already known — and when not to: for unfamiliar sites, use map_site first instead of crawling every page. This gives concrete routing guidance relative to siblings.
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.
Each tool targets a distinct operation: health checking, site mapping, single-page reading, multi-page crawling, and web search. The descriptions cross-reference each other to guide selection, leaving no ambiguity about when to use which tool.
All tool names follow a consistent verb_noun snake_case pattern: check_web_service, crawl_site, map_site, read_page, search_web. The naming style is uniform and predictable.
Five tools is a well-scoped set for a web reading service. Each tool covers a distinct need (discover, search, read, crawl, health check) and none feel redundant or superfluous.
The surface covers the full workflow: search to find URLs, map to discover site structure, read for single pages, crawl for bulk retrieval, and health check for service status. There are no obvious dead ends or missing core operations for the stated purpose.