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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered by structured data. The description adds that results are paginated and enumerates the returned fields, but with an output schema present, that enumeration is largely redundant. It says nothing about result caps, ranking, or rate limits, so it only modestly exceeds what the annotations and output schema already supply.

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 definition is a single front-loaded sentence with the search purpose stated first, followed by returned fields, pagination, and the alternative path. Every clause carries information and there is no filler. The semicolon-joined structure is dense but readable.

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 only two parameters, full schema coverage, an output schema, and read-only annotations, the description supplies what the structured fields do not: the choice between keyword search and direct lookup, plus pagination support. It omits any indication of page size or a cap on the number of pages, which would help an agent decide when to stop paginating.

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%, and the schema already explains keyword (name or keyword, e.g. NBA, 美食, and explicitly forbids passing content or profile URLs) and page_token (must come from the same user search's next_page_token with the keyword held constant). The description adds only the generic 'supports pagination' note, so the baseline of 3 applies.

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 and resource (按关键词查找今日头条用户) and lists the returned fields (用户 ID、名称、简介、粉丝数、认证说明), so the agent can distinguish this from toutiao_search_posts and toutiao_search_suggestions. It also signals the boundary with the direct-lookup siblings by saying that when a user ID or profile URL already exists, the agent should query the profile directly. It stops short of naming the sibling tools explicitly (toutiao_get_user_info_by_user_id / _by_profile_url), which would have made the distinction airtight.

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 states when to use this tool (you only have a keyword) and when not to use it (you already have a user ID or profile URL), which covers the main routing decision among siblings. The '支持分页' note plus the schema's page_token guidance covers continuation. It does not name the alternative tools directly, so the agent must infer which sibling to call.

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