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

Annotations only include openWorldHint: true, with no readOnlyHint or destructiveHint. The description uses '查询' (query), which implies a read operation, and includes pricing information (100 credits/run), which is a useful behavioral disclosure. However, it does not explicitly state that this is a non-destructive read-only operation, and it embeds pricing JSON in the prose rather than leaving it to structured fields. The description neither contradicts the openWorldHint annotation nor adds substantial behavioral context beyond the implication of 'query.'

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 description is moderately sized with a logical structure (purpose, included metrics, exclusions, examples, pricing). The example queries are valuable and earn their space. However, the pricing JSON blob is structured data that would be better placed in annotations/schema rather than prose, and the ambiguous '不包含' clause creates intentional-but-unclear exclusion phrasing. There is some redundancy between the first two lines (both restating the list of invested companies).

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?

Given 2 parameters, a full output schema, and openWorldHint annotation, the tool is moderately complex with many sibling tools. The description covers the park-scoped list purpose, the two-year window, and provides concrete examples. However, it fails to address the invest/invested direction ambiguity (key since park_invested_company_list is a sibling), does not clarify the year parameter's relationship to the two-year window, and the puzzling '仅返回数量不返回名单' clause leaves the return type uncertain. With the output schema present, return-value explanation is unnecessary, but these other gaps prevent a higher completeness score.

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 both park_name and year are already documented. The description adds the '近两年' (past two years) time-window concept, which is genuinely useful context for understanding how the year parameter operates. However, the relationship between the '近两年' default window and the optional year parameter is never clarified (does year override the window? interact with it?), and no syntax/format details are added. The description provides baseline value over the schema but nothing exceptional.

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 primary purpose is stated: querying a list of enterprises with external investments in the past two years for a specific park. The verb+resource is clear ('企业列表查询' with park-based filtering). However, the exclusion section contains '仅返回数量不返回名单' (only returns quantity, not roster) which directly contradicts the tool name being a list tool and the stated purpose of returning a '企业列表'. While likely intended to describe the _num siblings, the phrasing is genuinely ambiguous and could mislead an agent about whether this tool returns a list or a count.

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 '典型问法' (typical queries) section provides three concrete usage examples with real park names, which is helpful. The '不包含' section attempts to exclude other enterprise categories. However, it fails to disambiguate the most critical sibling distinction: park_invest_company_list vs park_invested_company_list (outbound investment vs received investment). The description's example context is adequate but it misses this key alternative, and the exclusion phrasing is vague ('其他企业分类的统计' could mean almost any sibling tool).

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