search

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

With no annotations, the description carries the full load and does well: it discloses the affiliate/search-engine data source and its noise, the translation side-effect when Chinese terms are used, and the compact line-based output shape. Gaps remain on pagination limits, rate limiting, and failure behavior.

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?

Front-loaded with the action and platform options, then the extra/field hint, then the return format. Compact and information-dense, though the multi-line dump reads like terse pseudocode rather than cleanly structured prose.

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?

An output schema exists so return values needn't be explained (they are anyway), and the description covers platform choice, keyword language, and the escape hatch for advanced filters. Only the page/pagination parameter and any auth or limit constraints are left unexplained.

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 0%, so the description must compensate, and it does for three of four parameters: platform values and their trade-offs, extra as overflow form fields with a pointer to superbuy_captures(grep='crawler'), and keyword implied via the Chinese-terms note. The page parameter is never mentioned, leaving one 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?

"Zoek op Superbuy" plus an enumeration of the three supported platforms (tb, 1688, xianyu) states a concrete verb and resource with scope. It also references the sibling superbuy_captures for form-field discovery, though it does not distinguish itself from siblings like details or superbuy_fetch.

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?

Gives actionable selection guidance: which platform fits which need (tb = noisy affiliate engine, 1688 = better relevance, xianyu = second-hand) and the tip that Chinese keywords work best because translation is skipped. No explicit when-not-to-use or routing to superbuy_fetch/details is provided.

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