searchSearch the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 5). | |
| query | Yes | The search query. | |
| scrapeResults | No | Also scrape each result to markdown, 1 extra credit per page (default false). | |
| preferStructure | No | Keep headings, lists and tables in each scraped result. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context about ranked results and the extra credit cost of scrapeResults, but does not disclose pagination behavior, query limitations, or the dependency of preferStructure on scrapeResults.
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 two sentences with no filler. It front-loads the core purpose and output format, then adds the optional scraping behavior and cost in a clear, compact way.
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?
With no output schema, the description adequately names the return fields (title, url, snippet). However, it lacks guidance on when to choose this tool over siblings, does not explain how preferStructure relates to scrapeResults, and omits any mention of pagination or result ordering beyond 'ranked'.
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 the baseline is 3. The description adds value beyond the schema by explaining that scrapeResults fetches each result as markdown and costs 1 extra credit per page, which is not present in the schema.
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 searches the web and returns ranked results with title, URL, and snippet. It is specific about the resource and output format, though it does not explicitly differentiate itself from sibling tools like images or extract.
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 provides no guidance on when to use this tool versus alternatives such as images, map, extract, or scrape. It mentions the scrapeResults option but does not explain when a user should prefer search over sibling tools.
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.
Most tools target distinct output types like search results, screenshots, images, or styleguides, but scrape and extract overlap significantly in pulling structured data from URLs. Brand and logo also intentionally overlap, with logo being a cheaper subset, though the descriptions do help clarify when to use each.
All tool names are short and lowercase, but they mix imperative verbs like extract, map, scrape, and search with noun-style names like brand, images, logo, and styleguide. There is no consistent verb-noun pattern, though the names remain readable and memorable.
Nine tools is a reasonable size for a web data-fetching server, and each tool covers a plausible retrieval mode. The set is not perfectly lean due to some functional overlap, but nothing feels excessive or redundant enough to hurt usability.
The toolset covers discovery via search and map, content extraction via scrape and extract, and visual/asset needs via screenshot, images, brand, logo, and styleguide. Minor gaps like PDF extraction or raw HTML retrieval exist, but agents can usually work around them.