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

Annotations only include openWorldHint: true, which is a weak signal. The description adds valuable behavioral context: it clarifies the tool covers macroeconomic indicators without company counts or POI details, mentions pricing and per-unit charging, and the schema notes version mismatch handling. Even though annotations are minimal, the description compensates well by setting expectations about data scope and billing behavior. Rating is 4 as it doesn't fully elaborate on return format or error cases, but the bar for transparency is higher without annotations and the description does a good job filling the gap.

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 main description is concise: two sentences stating purpose and scope, followed by a focused 'typical questions' line. The pricing block is separate and structural. While the pricing details are somewhat lengthy, they are structured and provide useful billing transparency. The description is front-loaded and efficient, earning a 4 not 5 only because the pricing paragraph adds a bit of extra length, but it's arguably necessary for the financial implications.

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?

The tool deals with macroeconomic indicators and has 3 parameters with a rich output schema (presence of output_schema signal helps). The description covers indicators scope, exclusions, example questions, and pricing, and the schema covers parameter semantics thoroughly. However, it doesn't fully explain how the tool behaves for different query modes (though schema mentions point/compare/rank/list/filter/peer_rank hints) or what exactly the output includes. Still, given the complexity and existing schema coverage, the description is reasonably complete, rating 4 rather than 5 due to minor gaps in operational details.

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 descriptions are comprehensive (100% coverage) for all three parameters, explaining versions as soft constraints, gov_names role by query type, and input_text purpose with examples. The description adds value by listing covered indicator categories and giving example query phrasings (e.g., '某市GDP'), which helps contextualize what input_text should contain. Since schema coverage is high, the baseline is 3, and the description's added examples and category list push it to 4.

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 it queries regional macroeconomic statistical indicators, listing specific covered categories (GDP/industry value-added, income & consumption, industrial activity, consumer prices, business environment) and explicitly excludes single-industry company counts and POI details. This provides a strong verb+resource+scope statement that distinguishes it from siblings like gov_data_enterprise_scale and chain_* company tools.

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 includes explicit guidance on when to use this tool (GDP, disposable income, cities over 1 trillion GDP) and what not to use it for (single-industry company counts—use market scale/change tools, and POI details). It also provides example query phrasings and notes that 'typical questions' are covered, giving clear usage context despite not naming specific sibling tool names.

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