web_html_generateFetch cleaned HTML for a web page URL.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Web page URL to fetch. | |
| waitFor | No | Wait for a CSS selector before extraction. Must be prefixed with "css:" (e.g. css:main). JavaScript wait conditions are not supported. | |
| scanFullPage | No | When true, scroll the page to load dynamically appended content (infinite scroll). Default false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the description is not burdened with safety disclosures. The description adds the qualifier 'cleaned' which hints that the HTML is processed/filtered, but it does not specify what cleaning entails (e.g., removing scripts, tags). It also does not mention potential issues like pagination or dynamic content beyond what the schema parameters (waitFor, scanFullPage) already cover. The description adds minimal behavioral context beyond the annotations.
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 a single, terse sentence with no fluff. It front-loads the core action ('Fetch cleaned HTML') and specifies the resource. However, it is almost too brief—given the tool has three parameters and nuanced behaviors (e.g., waitFor with CSS-prefix requirement, scanFullPage for infinite scroll), a sentence or two more would be justified. Still, it is efficiently concise without redundancy.
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 fetch tool, the description covers the essential input (URL) and output type (HTML). It does not, however, mention the output format explicitly (though 'HTML' implies a string), nor does it address error scenarios, rate limits, or the context of when to use this tool versus siblings. Given the presence of annotations (readOnlyHint, openWorldHint) and full schema documentation for parameters, the description is minimally adequate but lacks the contextual guidance an agent would benefit from when selecting among web-related tools.
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%, so all three parameters (url, waitFor, scanFullPage) are fully documented in the schema. The description only reiterates the URL purpose, adding no extra meaning or context about parameters. Since the schema does the heavy lifting, a baseline score of 3 is appropriate; the description provides no added value beyond what the schema already states.
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 clear verb and resource: 'Fetch cleaned HTML for a web page URL.' This unambiguously conveys the core function. However, it does not distinguish itself from sibling tools like web_markdown_generate or web_screenshot_capture, which are alternative output formats for the same retrieval task. Additionally, the title 'Generate web page HTML' conflicts slightly with the fetch-oriented description, but the description itself is clear.
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?
There is no guidance on when to use this tool versus alternatives such as web_markdown_generate or web_screenshot_capture. No mention of preferred use cases, exclusions, or trade-offs between HTML, markdown, and screenshot outputs. An agent would have no clue which tool to pick for a given scenario, relying only on the names and parameter schemas.
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 is clearly scoped to a specific platform and action (e.g., facebook_post_get vs instagram_post_get). Descriptions explicitly differentiate similar tools across platforms, and within-a-platform tools like tiktok_search_videos_list vs tiktok_search_hashtag_list have clear disambiguation notes.
All 167 tools follow a strict `platform_resource_action` pattern (e.g., youtube_video_comments_list). No mixing of styles—snake_case throughout, with consistent verb ordering (get, list, search, etc.).
The server has 167 tools, which is far beyond the typical well-scoped range of 3-15. While the broad multi-platform scope justifies many tools, this extreme number makes the tool surface overwhelming and difficult for an agent to navigate efficiently.
The tool set covers a wide range of platforms and operations including profile retrieval, post/video fetching, comments, search, transcripts, and ad library access. Minor gaps exist (e.g., no Facebook events or LinkedIn messaging), but the surface is comprehensive for a read-only data aggregation use case.