willow_web_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It discloses no API key requirement, the data source (HTML scraping), specific return fields, and the extra prerequisites for include_handoffs ('Requires web_net + consent.internet + a live egress lease'). It does not mention potential downtime or scraping limitations, but it is transparent about resource dependencies and filtering 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?

The description is concise, with a clear first sentence and a compact second paragraph. It avoids fluff and front-loads the core functionality. The parameter explanations are in-line but easy to scan. Minor density in the second paragraph keeps it from a 5.

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?

Given no output schema, the description lists return fields, which is helpful. It also covers use cases, filtering, and resource requirements. It does not detail pagination or error behavior, but for a web search tool the description is largely complete enough for an agent to invoke it correctly.

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 must compensate. It explains trusted_only and include_handoffs in detail, which are non-obvious. However, it does not describe app_id or max_results (though max_results is self-explanatory from name/default). Query is obvious. The description adds some value but leaves several parameters without explicit semantics.

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 action ('Open web search'), the specific resource ('DuckDuckGo HTML'), and the return structure ('title, url, snippet, source, and hostname per result'). It distinguishes itself from siblings like willow_institutional_search and willow_web_fetch by specifying it covers the 'live open web' and returns multiple result fields.

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?

Provides explicit use cases: 'current events, tech news, and queries that need the live open web.' This implies when to use it over alternatives, though it does not explicitly name a 'don't use' scenario or contrast with willow_institutional_search. The guidance is clear enough for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.