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

Beyond the readOnlyHint/idempotentHint/openWorldHint annotations, it discloses asset conventions (GLB, metres, +Y up, origin at base), the match-confidence scale (strong/good/weak) and the degraded-result signal, and the cost/licensing context (free with a free account). These are traits an agent cannot infer from the annotations or schema.

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 front-loaded, with the verb and resource in the first clause and practical gotchas following in descending priority. It is dense but nearly every sentence carries a distinct call-time decision; the licence sentence at the end is the weakest performer.

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 20-parameter, zero-required search tool with an output schema present, the description covers the decisions that matter most (semantic querying, size filtering, previews, weak-match fallback). Fine-grained filter interactions such as maps+format+source combinations are left to the per-parameter schema entries, which is reasonable.

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 moderate (65%) over 20 parameters, yet the description supplies the operational meaning several schema entries lack: it explains previews' max-6 cost tradeoff, the purpose of min_size_m with a concrete threshold, and derives the size_m convention that makes the size filters meaningful. That genuinely compensates for the coverage gap rather than restating the schema.

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 verb (search) and the exact resource set (CC0 3D models, PBR textures, HDRIs) plus the two mechanisms, semantic meaning and filters. It is immediately distinguishable from generate_model, get_asset and generate_texture among the siblings.

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?

It gives explicit when-to-call guidance (check size_m before placing, min_size_m >= 2 for floors and walls, previews are cheaper than downloading the wrong asset) and an explicit fallback: when no result beats 'weak', use generate_model instead. That is both a routing rule and an exclusion.

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