biz_list_metrics

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

With no annotations present, the description carries the full behavioral burden. It discloses a key limit: '本工具不执行任意 SQL，也不返回底层表结构以外的口径说明', clarifying it is a listing/metadata tool, not a query executor. It could go further by stating whether the list is dynamic or cached, but it does disclose the main boundary and the safety-relevant fact that it won't run arbitrary SQL.

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 tightly structured into four labeled blocks: definition, when to use, when not to use, prohibition. Every sentence adds distinct information with no filler, and the most important purpose statement is front-loaded.

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 its zero-parameter interface and the presence of an output schema, the description covers what it returns (metrics, 口径, granularity, sensitivity), when to use it, when not to, and a behavioral limitation. Nothing needed to invoke the tool correctly is missing.

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?

The tool takes zero parameters, so there is nothing for the schema to document and no parameter-level detail expected. The baseline for a no-parameter tool is 4, and the description appropriately focuses on the output rather than inputs, since no input semantics exist.

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?

Description opens with '【指标字典】列出业务层可查询指标、口径、粒度和敏感级', naming a specific verb ('列出'), resource ('业务层可查询指标'), and the attributes it exposes (口径, 粒度, 敏感级). This clearly differentiates it from sibling query tools like biz_query_sales and biz_anomaly_scan, which retrieve actual data rather than a dictionary of metric definitions.

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 '【何时用】' section explicitly tells an agent to use this tool when unsure what data exists and to avoid guessing table names, while '【何时不用】' explicitly routes known lookups (GMV/退款/花费) to biz_query_sales or biz_anomaly_scan. This is the most direct possible guidance, naming both conditions and alternatives.

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