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

Annotation openWorldHint: true indicates the tool may return unknown/unlisted values, and the description complements this by detailing the precise scope of indicators included and excluded. It adds behavioral context beyond the annotation by clarifying that it focuses on investment/financing interactions (state-owned, listed companies, cross-region) and does not cover other operational aspects. However, it does not describe return format or potential edge cases, which are partially covered by the output schema (present).

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 comprehensive but well-structured: it starts with the core purpose, then lists indicators, exclusions, and examples. It is longer than average but each sentence adds value for an agent to understand the tool's precise scope. The front-loading of purpose and explicit 'not for' statements make it efficient despite the length.

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 the tool's complexity (dozens of indicator types, many sibling enterprise_change_* tools) and the presence of an output schema, the description is highly complete. It enumerates all covered investment/financing indicators, explicitly excludes non-covered areas, and provides concrete example queries. This fully addresses versatility and ambiguity, making the tool self-explanatory for an agent.

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% as both company_name and country_name have descriptions and examples. The description reinforces the parameters with typical usage examples (比亚迪股份有限公司 with 中国, Tesla with 美国, etc.) aligning with schema examples. Since the schema already provides meaning, the description adds marginal value beyond what the schema conveys, warranting a baseline score of 3.

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 clearly states the tool queries investment and financing activity changes for a specific enterprise based on company name. It enumerates specific indicators (new outward equity investment, cross-region financing, interactions with state-owned/listed companies, etc.) and explicitly excludes other enterprise overview fields (financing round/stage) and branch setup/cancellation. This distinguishes it from the many sibling enterprise_change_* tools and provides concrete examples of typical questions.

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 gives explicit usage guidance: it is for investment/financing activity changes, not for general enterprise profile fields or branch changes. It explicitly lists what is not included (non-category indicators, batch screening by park/industry chain) and provides typical questions with specific company names, making it clear when to invoke this tool versus alternatives.

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