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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two pieces of context beyond that: results come from a real computation engine rather than LLM generation (a reliability/trust disclosure), and it enumerates what is returned (RR, OR, 95% CI), which matters because there is no output schema.

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?

A single compact sentence, front-loaded with the bracketed concept label followed by input form and outputs. Nothing is padded, though the '真实算法引擎执行，非大模型生成' clause is slightly tangential to the core purpose statement.

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?

All four required parameters are documented in the schema, the description fills the missing output-schema gap by listing RR, OR and 95% CI, and annotations cover the safety profile. What is missing is edge-case behavior (zero cells, continuity correction), which would matter for a statistical estimator but is not essential to invoke it.

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%, with all four parameters documented in Chinese (exposed/unexposed events and totals). The description only restates that the inputs are 2x2 table counts and adds no per-parameter meaning, format constraints, or zero-cell handling notes, 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 statistical resource (relative risk / odds ratio) and a specific operation (compute RR, OR and 95% CI from 2x2 table counts). An agent can tell this apart from nearby siblings such as act_roc or act_table_one, though no sibling is named explicitly.

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 clause '用户给的是四格表人数' implicitly tells the agent when to use this tool (when the input is four cell counts rather than raw data), which is real but indirect guidance. There is no statement of when NOT to use it, and no routing to alternatives like act_table_one or act_smd_balance for the same data.

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