open_web_pagesOpen up to four public pages and return clean Markdown evidence. Use a focused context to extract only what is relevant, or omit it to read the page directly.
| Name | Required | Description | Default |
|---|---|---|---|
| pages | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| pages | Yes | ||
| failures | Yes | ||
| budgetReached | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and destructiveHint, so there is no contradiction. The description adds useful constraints: it works on public pages, accepts up to four at once, and returns clean Markdown rather than raw HTML. This adds behavioral context beyond what the annotations alone provide.
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 with no filler. The core function is front-loaded in the first sentence, and the second sentence gives focused, useful guidance on the optional context parameter.
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?
Rich annotations and an output schema cover safety and return structure, and the description handles the main call shape and the context parameter. The undocumented 'live' and 'start' parameters and the lack of sibling-selection guidance leave real gaps for an agent trying to use every option correctly. Overall it is adequate but not fully complete.
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 0%, so the description carries the burden of explaining parameters. It compensates for 'context' by explaining that it focuses extraction and can be omitted for a direct read, and it reinforces the four-page limit. However, 'live' and 'start' remain unexplained, leaving a partial gap.
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?
States a specific action ('Open'), a clear resource ('up to four public pages'), and a distinct result ('return clean Markdown evidence'). The scope and output format set it apart from search_web and get_article, though it never names those siblings explicitly.
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 only usage advice is about the context parameter: use it for focused extraction or omit it to read the page directly. There is no guidance for choosing open_web_pages over search_web, get_article, or follow_feeds, so tool selection is left to inference.
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 has a largely distinct job: discovery (search_feeds, search_web), content retrieval/search within URLs (get_article, search_article), and library/feed management (save_article, follow_feeds, update_library_item, create_monitor). The only mild overlap is get_article vs open_web_pages, both of which extract content from public URLs, but their different output styles and intended use cases keep them mostly separate.
All nine tool names follow a consistent imperative verb + object pattern in snake_case: create_monitor, follow_feeds, get_article, open_web_pages, save_article, search_article, search_feeds, search_web, update_library_item. There are no mixed conventions, vague verbs, or surprising abbreviations.
Nine tools is well-scoped for a reading and summarization product: three search/discovery tools, three content-retrieval tools, and three library/feed management tools. Each tool contributes a distinct workflow step and the set avoids bloat.
The set covers discovery, fetching and searching content, saving to a library, following feeds, monitoring page changes, and updating library items. However, there are no removal operations (unfollow feed, delete monitor, delete library item) and no direct way to list or read the user's saved library or followed sources, creating noticeable lifecycle gaps.