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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the exact computation (poverty line minus income plus 1.5 MRP per child aged 1–6, from application month to quarter end), the fact that it is advisory rather than authoritative, and the legal basis (MTSZN order No. 160, 35% median / 70% subsistence minimum).

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 purpose and Russian/Kazakh aliases, then scope limits, then the calculation and legal rule. Dense but each sentence carries substantive information; the trilingual title line and long legal citation add some length without much agent value.

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 compensates by spelling out what the tool returns (monthly and quarterly amounts and the formula) and by stating the authority/eligibility boundary, which is exactly what an agent needs to interpret the result and not overstate it.

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 baseline is 3, but the description adds real meaning for poverty_line_kzt: it is regional, changes every quarter, must come from the user or an official source, and is legally defined as the larger of 35% of median income and 70% of the regional subsistence minimum. It also explains application_month's role in fixing remaining quarter months.

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 and resource ('Tests the income criterion for targeted social assistance (АСП) in Kazakhstan and estimates the monthly and quarterly amount'). Clearly distinct from sibling tools such as kz_mrp_convert or kz_salary_gross_to_net.

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?

Gives explicit scope boundaries: 'It does not decide eligibility: the family survey, employment measures, social contract and refusal grounds are decided by the authority.' Also instructs the user to supply the poverty line rather than guess. It does not, however, name an alternative sibling tool or state when another tool would be preferable.

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