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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: a per-call cost of 20 points and the 20-results-per-page pagination limit, which are not derivable from structured fields. It omits any note on rate limits or failures, but the added cost signal is valuable.

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 core facts (keyword search, returned fields, pagination, cost) are front-loaded and useful, but the same content is restated in both English and Korean, which doubles length without adding information. Structure is acceptable but not tight.

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 readOnly/openWorld annotations, a fully documented 2-param schema, and no output schema, the description covers purpose, return fields, pagination range, and cost. Only the routing to sibling search tools is missing, which is a minor gap for a callable search endpoint.

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 both keyword and page are already documented in the schema. The description only adds that page ranges allow iterating through results, which the schema already implies (1~5, 20/page). Baseline 3 is appropriate when the schema carries the meaning.

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+resource ('Google image search by keyword') and enumerates the returned fields (image URL, source link, title), which distinguishes it from google_search and google_news_search by the 'image' resource. However, it never explicitly names those siblings or clarifies the boundary with google_lens_search, so differentiation is implicit.

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 description explains pagination mechanics ('page 로 결과 페이지를 넘겨 가며 조회') but gives no when-to-use guidance, no exclusions, and does not route the agent to or away from alternative search tools. An agent must infer the choice purely from the resource noun.

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