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

The description adds significant behavioral context beyond annotations: it states the cost ($0.01/call), determinism, that it cites primary sources, and that errors/unverified rules are never billed. This is not present in the annotations (which only declare readOnlyHint false, idempotentHint true, etc.). No contradictions with annotations.

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 concise and well-structured: it opens with the core purpose, then pricing, then behavioral guarantees. Every sentence adds value without redundancy or fluff.

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 has 8 parameters and no output schema, the description should clarify the return value or the two modes (payment requirements vs execution). While the parameter description for x_payment explains the payment flow, the tool-level description does not mention what it returns when executed. The core purpose is clear, but an agent might not know if the result is a number or a breakdown, which is a notable gap.

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%, so all parameters are documented. The description adds meaning by explaining that 'previous month salary' is used for the withholding table lookup and that the official rate table is applied, connecting parameters to the calculation logic. However, it does not elaborate on each parameter or the payment flow, so it only slightly adds beyond the schema.

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 computes 'Bonus net pay' from 'social insurance and withholding tax' using an 'official rate table' and 'previous month salary'. This is specific and action-oriented, and the reference to 'bonus' distinguishes it from sibling tools like jp_payroll_net which handle regular payroll.

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 implies usage for bonus calculations by mentioning 'based on previous month salary', but it does not explicitly state when to use this tool versus alternatives like jp_payroll_net or jp_social_insurance. There is no 'use this when...' or exclusion of other tools, so the guidance is only implied.

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