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

With no annotations, the description carries the full burden and does substantial work: it discloses the statutory contribution model (Pension 16%, Medical 6-10%, Housing Fund 5-12%, Unemployment 0.5%, Work Injury 0.2%) and the municipal floor/ceiling rule (60%/300% of average wage) across 20+ cities. It also reveals that omitting salary triggers an internal market P50 lookup, which is non-obvious behavior. It stops short of saying what the returned figure contains or whether it is monthly vs. annual.

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?

Two sentences with the calculation scope front-loaded and the input-mode behavior second; there is little filler. The parenthetical rate list is dense but each figure earns its place by defining what 'all-in' means.

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 7-parameter calculator with no output schema and no annotations, the definition explains inputs and cost composition well but never states the shape of the result — whether it returns a total, a per-component breakdown, monthly or annualized figures, or how headcount and bonus_months combine into the number. Given the absence of an output schema, that return-context gap matters more than it would elsewhere.

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 the baseline is 3 and the schema already documents city, role, headcount, seniority, bonus_months, housing_fund_rate, and monthly_salary_cny. The description adds one genuinely new fact: the fallback path resolves via market median P50, clarifying the interaction between monthly_salary_cny and role beyond the schema's 'role must be provided' note. That is an incremental addition, not enough to lift far above baseline.

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 opens with a specific verb and resource ('Calculate total all-in employer headcount cost in China') and enumerates the cost components it covers, so the tool's scope is unmistakable. It does not name or contrast with any sibling such as calculate_compensation_arbitrage or get_salary_trend, leaving differentiation to inference.

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?

It signals two input modes — an explicit monthly_salary_cny or a role/city market-median lookup — which is useful conditional guidance for how to call it. However, there is no statement of when to prefer this tool over a sibling cost or salary tool, and no exclusions or prerequisites.

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