scene_search_assets

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

Annotations already cover the safety profile (readOnly, non-destructive, closed world), and the description adds real value beyond them: it enumerates the returned fields (id, name, group, icon, model size, hasImage, presetStatus), explains what presetStatus means for 交互机关 assets, warns that names are duplicated, and documents the didYouMean fallback on empty results. Pagination/limit-default behavior is left unmentioned, which keeps it from a 5.

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 purpose is front-loaded in the first sentence, but the remainder is a run-on stream joined by semicolons, mixing return fields, dedupe advice, id usage, batching, and didYouMean with no paragraphing. The clause 'The id of an asset as query finds that asset (its size, its group)' is garbled and costs the reader effort.

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 7-parameter, 0%-documented, output-schema-less catalog search over 2468 entries, the description supplies most of what an agent needs: what matches, the multi-query pattern, the ambiguous-name pitfall, what comes back, and what to do on zero hits. Only pagination (limit/offset) and explicit min/max size naming are missing.

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 carry the params, and it partially does: `query` (words in Chinese or icon name), `queries` (multi-search with a literal example array), `group`, and size in metres via 'longest side'. `limit` and `offset` are never mentioned, and minSize/maxSize are only implied by 'by longest side in metres' rather than named.

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 and resource: 'Search the full catalog of 2468 official placeable assets (trees, houses, fences...)' and names the matching dimensions (Chinese name/icon name, group, longest side in metres). The examples of asset types and the pointer to scene_asset_images / scene_build_blocks make it distinguishable from catalog siblings like scene_block_catalog and image_catalog.

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 concrete workflow guidance: 'look at them with scene_asset_images before choosing' and 'Use the id as template in scene_build_blocks', plus the batching advice that one or two calls with `queries` replace twenty. It never states when NOT to use it (e.g. blocks vs. assets, or when scene_block_catalog is the right catalog), so it stops short of explicit exclusions.

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