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

Annotations already establish readOnly/idempotent/non-destructive and closed-world, so the description does not need to re-litigate safety. It adds real behavioral context the annotations don't: the catalog is pre-made models (not user projects), results render as a clickable grid that opens in 3D, and plain-word fuzzy matching is expected. It does not state what happens on zero matches or how ranking works.

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 purpose and corpus scope, then query guidance, then return shape — a sensible order. The 18-item category parenthetical is long and borders on list-dumping, but each item contributes to helping an agent decide whether the model it wants exists here.

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?

Search tools live or die on query formulation and result shape, and the description covers both (return fields id/name/size/picture plus the grid UI). Nothing critical is missing for a simple 3-param read tool; only edge-case behavior (no results, ranking, why `limit` defaults to 8) is left to the schema.

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 the baseline is 3 and the schema handles field-level meaning. The description still earns credit by showing what a good `query` looks like ("kraft paper bag", "tuck end box", "hộp quà Tết"), which conveys the multilingual, multi-word-but-short query style better than the schema's one-liner.

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 and resource ("search Drint's library of ready 3D packaging and print mockups") and bounds the corpus (~1000 models, enumerated categories). An agent can distinguish this from open_mockup, list_dielines, or get_dieline purely from the text.

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 usage guidance for the query ("a few plain words for the product") with four worked examples, which is the main thing an agent needs to call this correctly. It never names the alternative for the obvious next step (open_mockup to open a found model), so routing is implied rather than stated.

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