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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add substantive context: monthly publication granularity, a 12-full-month win-share window, first vs second instance split, median claim-to-judgment time, and links to full texts. It also sets expectations with 'statistics of published rulings, not legal advice' and 'each ruling concerns one contract', which prevents over-reading results. It stops short of stating anything about recency of the underlying data or how the 12-month window is anchored.

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 purpose, which is good, but it is a single sprawling sentence that then enumerates enum codes and return fields at length. The category glosses duplicate the enum, and the return-field inventory partly overlaps the output schema, so some of the bulk does not fully earn its place.

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 two-optional-parameter statistical tool, the description covers subject scope, category taxonomy, return shape, and interpretive caveats — more than enough to call it correctly. Since an output schema exists, the detailed return-value listing is somewhat redundant, but it is not harmful. Minor gap: no hint about data freshness or update cadence.

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 baseline is 3, but the description earns above baseline by glossing every enum value — chf as CHF mortgages, waluta_inna as EUR/other-currency loans, skd as the art. 45 free-credit sanction, wczesniejsza_splata as cost refunds after early repayment/Lexitor, wibor as WIBOR clauses, polisolokata as unit-linked policies. That mapping is genuinely useful meaning an agent would not get from the bare enum codes. The `limit` parameter is only echoed, not enriched.

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 (statistics of court rulings in consumer credit disputes) with scope (Polish common courts, Ministry of Justice portal, finwire.pl classification). It is clearly distinguishable from siblings like get_tax_rulings or get_legal_changes by naming the exact subject matter and data source.

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?

Usage is implied rather than stated: an agent can infer this answers questions about borrower win rates in Polish credit litigation, and the description notes 'omit for all categories' implicitly via the schema. It never names an alternative tool or states when not to use it, so routing relies on inference from the sibling list.

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