Search

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

With no annotations, the description carries the full behavioral burden. It discloses verified headless behavior, bot-challenge risks for duckduckgo/brave, yahoo's equivalence to Google due to licensing, and the automatic private virtual display when headless=False. It does not cover failure modes or rate limits, but the disclosed operational behavior is valuable.

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 appropriately sized and front-loaded with the core purpose, followed by line-broken parameter guidance. It is dense but mostly earns its length; minor redundancy exists because it restates defaults already present in the schema, and the SPEC.md reference may not be accessible to all agents.

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 annotations and no schema descriptions, the description covers the important operational details: engine alternatives, headless behavior, profile discovery, and display handling. The lack of num_results semantics and absence of error/blocking behavior are the main gaps; output schema covers return values, so that is not a concern.

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 engine with allowed values and caveats, profile with a reference to list_profiles, and headless with default and display behavior. However, num_results is not described, and query is only implied by the search phrasing.

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 verb and resource: search with a search engine and return a list of titles/URLs/snippets. This clearly distinguishes it from sibling tools such as fetch_page, which fetches page content rather than returning search-result snippets.

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 gives clear operational guidance: engine selection, recommendation to avoid headless for duckduckgo/brave, and use of yahoo as a fallback when Google is blocked. It does not explicitly state when to use search instead of sibling tools like fetch_page, but the engine-level guidance is specific and practical.

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