xhs_search_images

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

Annotations only supply readOnlyHint and openWorldHint. The description adds substantial behavior beyond them: each item is an image tied to a note with possible multiple images per note (deduplication semantics), ranking is by platform relevance, exact keyword inclusion is not guaranteed, recall is not guaranteed, and pagination via page_token is best-effort. This is exactly the kind of honest behavioral disclosure the dimension rewards.

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?

Purpose is front-loaded and each clause carries weight (routing to siblings, pagination caveat, ranking/recall caveats). It is a dense run-on paragraph, however, and the multi-clause structure is slightly harder to scan than a bulleted or split form would be.

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-value documentation is not needed. Combined with the annotations, the description covers routing, pagination, ranking, and recall limits, leaving nothing an agent needs to call this tool correctly.

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 100%, so both parameters are already documented, giving a baseline of 3. The description adds a genuine nuance beyond the schema on page_token ('可用于尝试下一页，不保证下一页有结果'), clarifying that pagination may yield no results. That extra meaning lifts it above baseline.

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?

States a specific verb+resource+scope (搜索小红书图片 / search Xiaohongshu images by keyword). It explicitly distinguishes itself from sibling tools: detail tools for when a note link/note_id already exists, and xhs_search_notes variants for image-text vs video notes. An agent can route correctly without opening any schema.

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 explicit when-to-use (keyword image search), when-not-to-use (already have link/note_id → detail tools), and names the two concrete alternatives with parameters (xhs_search_notes(note_type="image") and note_type="video"). Nothing is left to inference.

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