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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely useful context beyond them: the half-yearly cadence of the source data, PLN as the unit, the caveat that the % -of-limit series is measured in December states, and a not-investment-advice disclaimer. It says nothing about pagination or freshness of the latest half-year, but the output schema covers return shape.

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 resource and data source, then a dense but scannable enumeration of covered metrics, closing with the alternative-tool pointer and disclaimer. The middle sentence is long and comma-heavy, but for a data-catalog tool with many series it earns its length; nothing is redundant.

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 read-only single-parameter data retrieval tool with a rich annotation set and an output schema, the description supplies everything an agent needs: what data is returned, the source and cadence, units, the special December-state caveat for one series, and where to go for the complementary legal-limit data.

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?

There is a single optional parameter with 100% schema description coverage (number of past half-yearly states, default 6), so the schema already carries its meaning. The description corroborates the half-yearly granularity of the series but adds no new semantics such as what history=0 returns or how the window interacts with the 'since January' metrics. Baseline 3 is 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 resource (IKE and IKZE Polish retirement accounts from half-yearly KNF data) and enumerates exactly what is measured: account counts, assets by institution type, contributions, withdrawals, holder demographics, and the finwire_ike_ikze_avg_balance index. An agent can distinguish this from get_pension_stats, get_ppk_stats, and get_legal_limits without opening any 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?

Explicitly routes the agent elsewhere for one adjacent need: 'For the contribution limits themselves use get_legal_limits.' It also frames the data as informational reference material. It does not, however, distinguish itself from near siblings get_pension_stats, get_ppk_stats, or get_investment_funds, leaving that inference to the agent.

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