datalab_shopping_keywords

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

No annotations exist, so the description carries full behavioral burden. It usefully discloses the find_category dependency and shows a concrete comparison scenario, but says nothing about the return values (relative search index/ratio vs. raw counts), any cap on the number of keywords, or behavior for invalid category codes.

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, followed by the prerequisite, business cases, and a concrete example. The trailing Korean sentence is a near-duplicate of the find_category instruction, which is mild waste, and the emoji adds no semantic content.

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 five required parameters and no output schema or annotations, the definition should explain the returned metric and any keyword-count limit; neither is covered. The find_category linkage and example partly compensate, leaving it adequate but with clear gaps for an analytics tool.

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 100%, so the baseline is 3. The description adds real value for `category` by tying it to find_category and for `keyword` by demonstrating the name/value pair form ('원피스' vs '자켓' vs '드레스'), but contributes nothing about `timeUnit` granularity or date-range limits.

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: "Compare specific keywords within a shopping category", which is materially different from the sibling aggregation tools (datalab_shopping_category, datalab_shopping_by_device). It does not, however, distinguish itself from the closest siblings datalab_shopping_keyword_by_device / _by_gender / _by_age, which share the same keyword-comparison shape.

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 prerequisite "Use find_category first" (repeated in Korean) is an explicit ordering constraint that prevents a common failure with the required category code. Business cases (keyword optimization, competitor analysis, trend identification) give context, but the description never tells the agent when to choose this over the by_device/by_gender/by_age variants.

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