web_search

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

Annotations already declare readOnlyHint and openWorldHint. The description adds meaningful behavioral detail by promising 'truthful empty/partial status' and describing the return contents. There is no contradiction with the annotations, and the added transparency about partial results is useful.

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 and well-structured: first sentence states the purpose, second sentence describes return values, third sentence directs to the sibling tool. No unnecessary words or redundant content.

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 covers the tool's core purpose and return fields and references the sibling tool, but it lacks explanations for important parameter semantics (mode, vertical, freshness) and provides no output schema. This leaves gaps in the agent's understanding of how to fully leverage the tool.

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?

Only the queries parameter has a description ('One to three focused public-web queries'). The mode, vertical, and freshness parameters are left unexplained beyond their enum values, and the tool description does not compensate by explaining their intended usage or impact on results. This sparse coverage is a significant gap for an agent selecting parameter values.

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 purpose: 'Discover public web sources for focused questions.' It specifies exact return contents (ranked source URLs, snippets, evidence_id) and contrasts with web_fetch by saying 'Use web_fetch to read a known URL,' making the distinction from the sibling tool explicit.

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 implicit usage guidance: use web_search to discover sources for focused questions, and use web_fetch to read a known URL. This is helpful but could be more explicit about when to choose web_search over web_fetch and when to use different modes or freshness values.

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