browse_searchSearch the web via DuckDuckGo and return compact title, URL, and snippet rows without ads. Filter results to one site and run parallel searches for quick research.
Web search (DuckDuckGo), background tab: "n. title | url | snippet", no ads; site: one domain. Parallel OK.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | default 8, max 20 | |
| site | No | ||
| query | Yes |
Changes observed during successful MCP inspections.
v0.5.11Input schema / properties / max / descriptionPrevious value: -"results, default 8, max 20"New value: +"default 8, max 20"Input schema / properties / siteAdded value: +{
+ "type": "string"
+}v0.5.8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does disclose meaningful traits: runs in a background tab, returns no ads, and emits a numbered "n. title | url | snippet" format. It omits operational risks that matter for a DuckDuckGo scraper, such as rate limiting/blocking, whether the tab is closed afterward, or failure behavior.
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?
Barely more than a sentence and front-loaded with the core identification ("Web search (DuckDuckGo)"), so there is no waste. The telegraphic semicolon-chained style hurts readability slightly compared with plain phrasing.
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 three-parameter, read-only search tool with no output schema, the definition supplies the backend, output format, ad behavior, and concurrency tolerance, which covers what an agent needs to invoke it. Only failure/rate-limit context is absent.
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 only 33% (only `max` is documented,"default 8, max 20"). The description partially compensates by clarifying that `site` restricts results to a single domain, but it adds nothing about `query` or the result-count interaction with a site filter.
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 verb and resource ("Web search") plus the backing engine (DuckDuckGo), which is enough to separate it from retrieval-oriented siblings like browse_read or browse_open. It does not explicitly compare itself to those siblings, keeping it below a 5.
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 explicit when-to-use or when-not-to-use guidance and no named alternative among the browse_* siblings (e.g., when to search vs. open a known URL). Only indirect usage hints appear ("site: one domain", "Parallel OK"), which a caller must infer apply to searching.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.