search_assets

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

With no annotations, the description carries the full burden, and it does disclose genuinely useful behavior: sources are CC0/openly licensed, and photo results include the attribution text an agent must carry forward. It omits pagination/result-count behavior, whether queries are fuzzy or keyword-based, and whether returned URLs are temporary, which matters for a search tool with a default limit of 12.

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 opening sentence states the purpose immediately, and the per-kind breakdown is compact and scannable despite spanning several lines. Every line adds information; nothing is filler.

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?

With 4 optional parameters, no output schema, and no annotations, the description covers purpose, kind values, licence syntax, and the follow-up import call — enough for an agent to invoke it correctly on the first try. The missing pieces are minor: `limit` behavior and what the result list looks like.

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% and there are no enums, so the description does significant lifting: it enumerates the valid `kind` values with a one-line rationale for each and shows the exact `licence` string format ('cc0,pdm' vs 'by,by-sa') with the attribution implication. It leaves `limit` and `query` semantics completely unexplained, which is the main 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?

The description names a specific action (find/search) and resource (free real-world material), then enumerates the three asset kinds it covers — Poly Haven textures, Poly Haven HDRIs, and Openverse photos — so an agent can tell exactly which content pool it queries. It does not explicitly differentiate from other image-producing siblings like generate_image, but the 'free real-world material' framing distinguishes it from generative tools.

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 closing line 'Then import_asset(id, kind)' gives a clear workflow hook, telling the agent this is a discovery step that pairs with import_asset. However, there is no explicit guidance on when to prefer this over generate_image or create_artwork, and no note about what to do when a search returns nothing.

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