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

Annotations already cover read-only and open-world behavior, so the bar is lower; the description adds a concrete cost signal ('호출당 7포인트'), which is genuinely useful behavioral context an agent cannot get from structured fields. It does not discuss result volume, pagination behavior, or failure modes.

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 the verb and resource in the first clause, followed by return fields and cost — a sensible priority order. The Korean restatement duplicates the English, which is a small amount of redundancy but serves a bilingual audience.

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 no output schema, the description correctly compensates by naming the returned fields, and it discloses the per-call point cost. Only soft gap is that it says nothing about result count or page traversal, though the schema documents the page parameter.

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% (keyword 1~200 chars, page 1~10 default 1), so the schema already carries parameter meaning. The description only restates 'for a keyword' and adds nothing beyond it, which is the baseline 3 case.

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 ('Google Shopping search') and enumerates the returned fields (title, price, shop, rating, link), so an agent knows exactly what kind of result it gets. It does not, however, distinguish itself from the shopping siblings (naver_shopping_product, coupang_product, amazon_product) which are the most likely source of confusion.

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?

Usage is implied by 'for a keyword' — i.e. use this when you have a product search term — but there is no explicit guidance on when to prefer it over naver_shopping_product or coupang_product, and no mention of prerequisites. Adequate for a simple, self-evident search tool, but no routing help.

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