web_search

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

With no annotations provided, the description carries the full burden. It successfully discloses the key behavioral trait that results are processed/synthesized by an LLM rather than returned raw. However, it omits rate limits, authentication requirements, error handling behavior, and whether the LLM synthesis incurs additional latency or costs.

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 front-loaded with the core purpose first, followed by an 'Args' section documenting parameters. While the 'Args:' format is slightly informal, every sentence earns its place and the structure is scannable for an LLM agent.

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 the tool has an output schema (not shown), the description appropriately avoids explaining return values. It covers the search engine specificity (SearXNG), the synthesis behavior, and parameter semantics necessary for invocation, though it could benefit from mentioning error scenarios or domain format requirements.

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%, requiring the description to compensate entirely. It documents all 4 parameters (query, max_results, allowed_domains, blocked_domains) with clear semantic meaning. However, it states max_results has a 'default: 10' which contradicts the schema's 'default: null', creating a potentially costly ambiguity for the agent.

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 'Search[es] the web using SearXNG, fetch[es] top result pages, and synthesize[s] with LLM.' This distinguishes it from sibling 'webfetch' (likely raw fetching) by specifying the SearXNG engine and the LLM synthesis step, providing specific verbs and resource scope.

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?

While there is no explicit comparison to siblings, the phrase 'synthesize with LLM' implies usage context—use this when synthesized search results are needed versus raw page fetching. However, it lacks explicit 'when to use vs webfetch' guidance or prerequisites.

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