search_web

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

There are no annotations, so the description carries the full behavioral burden. 'Live internet' conveys that the search is current and networked, but the description does not disclose the result format, result count, pagination, failure modes, or whether it is read-only. For a tool with no annotation support, this is thin.

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?

A single, front-loaded sentence that wastes no words and communicates the tool's purpose immediately.

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 tool is simple with one required parameter, so the description is adequate for constructing an invocation. But with no output schema and no annotations, it omits what the agent should expect in the response and how this relates to the sibling fetch_webpage.

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 100% and the query parameter is already described as 'Search query terms.' The description adds relevant examples of query intent (docs, code, versions, errors) but no format or syntax beyond what the schema provides, so it meets the baseline.

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 specific action (search) on a specific resource (the live internet) and lists concrete content categories (documentation, code examples, API references, library versions, error solutions). It distinguishes itself from the mostly local/system sibling tools, though it does not explicitly contrast with fetch_webpage.

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 listed use cases imply when to use the tool: when the agent needs current web documentation or error fixes. However, it gives no explicit guidance on when not to use it or when fetch_webpage would be a better choice, leaving selection to inference.

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