web_search

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

With no annotations provided, the description carries the full transparency burden. It discloses the browser fallback chain (Chrome → Firefox → ... → system default), explains that the query is not pre-escaped, and mentions the default engine and optional bundle_id override. This adds meaningful behavioral context beyond what structured fields could convey.

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 well-structured: a one-sentence purpose, a usage/speed note, the fallback chain, and a concise Args list. Every sentence adds value—no redundancy or filler. The length is appropriate for the four parameters and behavioral nuances.

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?

The description is complete for the tool's complexity: it covers all four parameters, explains browser selection behavior, gives usage context, and even includes an example for bundle_id. Since an output schema exists, no return-value explanation is required. There are no obvious gaps that would leave an agent uncertain.

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?

The input schema has 0% description coverage, but the Args section compensates fully by explaining each parameter: device format ('ADB serial or ios:<udid>'), query semantics ('Free-text search terms'), engine values ('google', 'ddg', 'bing', 'brave'), and bundle_id purpose ('Optional iOS browser bundle id override'). This is exactly the kind of clarification an agent needs.

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's function: 'Open a web search in whatever browser is on the device.' It goes beyond a generic verb by specifying the resource (web search) and the mechanism (browser on device). It also distinguishes itself from related tools like launch_app or open_url by focusing on search queries and the 'search for X' use case.

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 explicit usage guidance: 'Useful when the user asks "search for X" or you need to look up info that's not on the current screen.' It also compares the tool to a slower manual sequence (launch Chrome → tap address bar → type → submit), which helps the agent choose this over manual UI steps. It doesn't explicitly name sibling tools as alternatives, but the context is sufficient.

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