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

Annotations already declare this a read-only, idempotent, closed-world operation, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it pins the calculation to the 2026 tax code and a specific 7-level progressive rate table, telling the agent the result is a deterministic statutory computation rather than an estimate. It does not discuss rounding/precision or what the output contains, but the output schema covers returns.

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 front-loaded sentence stating the domain, the legal basis, and the supported modes, with no filler or redundant restatement of the tool name. Nothing can be removed without losing scope information.

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?

For a 13-parameter tool, the description correctly frames the domain and the three modes while leaving parameter-level detail to a fully covered schema and return values to the output schema. The only gaps are cross-tool routing and any caveat about which mode-specific parameters are ignored, both minor given the surrounding structure.

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% and the schema descriptions already explain each parameter's role per mode, including the 80%/56% inclusion rules and the annual-vs-monthly override precedence. The description only names the three modes, which the mode enum already documents. With the schema doing all the heavy lifting, baseline 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 gives a specific verb+resource ('精准计算中国个人所得税') and names the exact tax regime (2026 现行税法, 7 级超额累进税率表) plus the three computation modes it supports. An agent can tell this is a tax-calculation tool, not a lookup or policy-query tool. What it lacks is an explicit boundary against close siblings such as calculate_salary_take_home or compare_annual_bonus_tax.

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 enumeration of the three modes (月度累计预扣 / 劳务报酬预扣 / 年度汇算清缴) implies which scenarios the tool covers, which is real usage guidance. However, it never states when to prefer this over calculate_salary_take_home or compare_annual_bonus_tax, nor any prerequisites or exclusions. Usage is therefore inferable but not directed.

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