SearchPipe

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

With no annotations provided, the description carries the full burden and delivers richly: it discloses the commercial pipeline (authentication, rate limiting, input/output moderation, credit charge, refund on failure, usage logging), the per-call credit charge, the AI-generated marker, the Tavily-style return shape, and the exact error conditions. This is exemplary behavioral disclosure for a billing-eligible tool.

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 longer than average but every sentence earns its place: purpose, pipeline, commercial flow, parameter note, return format, error cases. It is front-loaded with the core purpose and organized into logical paragraphs, with no filler or repetition.

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?

For a complex commercial tool with billing, moderation, and authentication, the description covers nearly everything an agent needs: mechanism, credit implications, failure modes, and return structure. An output schema exists for return values, so the return-format note is a bonus rather than a requirement. Minor gaps are only the unmentioned optional parameters.

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 fully explains api_key (prefix, environment variable fallback, precedence) and implies query's role, and 'optional AI answer' hints at include_answer. However, max_results, include_raw_content, and the remaining behavior of include_answer are not addressed, though their self-descriptive names mitigate the gap.

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?

Opens with a specific verb+resource ('Run an AI-powered web search for a query') and details the full pipeline (SearXNG retrieval → page fetching → LLM reranking → optional AI answer). This leaves no ambiguity about what the tool does, even without sibling tools for contrast.

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 intended use is implied clearly by the opening statement (AI-powered web search when you need retrieved and reranked web content), but there are no explicit when-to-use/when-not-to-use instructions or named alternatives. With no siblings listed, the absence is less damaging, yet the description never states conditions that would make this tool inappropriate.

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