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

Annotations already establish readOnly, idempotent, non-destructive behaviour, and the description goes further by disclosing the rounding contract ('smallest whole-tenge gross whose rounded net equals the target') and the returned withholding/contribution breakdown. Withholding rules are delegated to the schema's parameter descriptions, so it stops just short of full behavioural coverage.

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 trilingual label line is front-loaded and the second sentence packs scope, semantics and return contract efficiently with no filler. Slightly redundant for a reader who only needs one language, but nothing is wasted.

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 no output schema, the description correctly compensates by describing the return value (smallest qualifying gross plus full withholding/contribution breakdown), which is the essential missing piece. It omits how ties or out-of-range inputs behave, but the schema bounds cover those adequately.

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%, so the schema already explains lang, employee_type, born_before_1975 and apply_base_deduction in detail. The description only clarifies the target-net concept ('на руки') and adds no syntax or edge-case detail beyond the schema, making the baseline 3 appropriate.

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 transformation (find monthly gross from a target net) with the exact country and year scope, and effectively distinguishes itself from the inverse sibling kz_salary_gross_to_net through the direction of the calculation. An agent can tell exactly what comes out without opening the schema.

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 scenario is implied by 'employee receives a target net amount', so an agent can infer when the tool applies, but there is no explicit when-to-use/when-not guidance and the inverse sibling kz_salary_gross_to_net is never named as the alternative for the opposite direction.

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