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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds useful behavioral context — itemised local tax names, effective and marginal rates, step-by-step workings, and bonus-comparison output — which is valuable since there is no output schema. It stops short of stating assumptions or error behavior (e.g., unsupported city, non-CNY inputs).

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?

Front-loaded with the core computation in the first clause, followed by a dense but purposeful coverage list. The colon-separated enumeration is efficient, though it reads as a feature dump rather than prioritized guidance, and 'with its local name' phrasing is slightly verbose.

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?

With 11 parameters, no output schema and no per-parameter behavior in annotations, the description does the right work by enumerating what the output contains (itemisation, effective/marginal rates, employer cost, workings). It is nearly complete, missing only explicit default/edge-case behavior and any cross-reference to the overlapping sibling tools.

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% and includes enums, defaults, min/max and Chinese deduction amounts, so the schema carries parameter meaning. The description adds only framing-level semantics — that deductions are 'special additional', that bonuses can be taxed separately or together, and that allowances apply to foreign nationals — without deepening any individual parameter 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?

States a specific verb+resource+scope: take-home pay for an employee in China from a gross yearly salary in CNY under 2026 rules. It also distinguishes itself implicitly from siblings by making clear it is the net-from-gross direction, while sibling names like gross_for_target_net and employer_cost cover the inverse and employer side.

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 'Covers:' list implies the scope of use (IIT, contribution bases, special deductions, bonus, expat allowances), so an agent can infer when this tool applies. However there is no explicit when-to-use/when-not guidance and no routing to siblings, even though the description promises 'employer cost' output that may overlap with the employer_cost tool — that overlap is left unresolved.

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