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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that: it declares the data source (EUREKA / Ministry of Finance), the aggregation cadence ('counts per full week', 'provisions cited most often in the last 52 weeks'), and a semantic caveat that rulings are single-taxpayer answers, not legal advice.

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 use case, then provenance, then the topic list, then the return shape and the caveat — a sensible ordering with no filler. It is dense and list-heavy in one long paragraph, and the slug list partially duplicates the enum, but the glosses justify most of the length.

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-parameter read-only query with an output schema, the definition covers what the tool is, when to use it, the full topic taxonomy, what gets returned (weekly counts, top-cited provisions, newest rulings with signature/authority/dates/thesis/link), and the interpretive limits. Nothing an agent needs to invoke it correctly is missing.

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, but the description adds real meaning by glossing each Polish enum slug in plain language (najem_prywatny = private rental, sprzedaz_nieruchomosci = selling a flat and housing relief, jdg_ryczalt = sole proprietorship/lump-sum/IP Box). It does not explain the limit parameter's cap or the default beyond what the schema already states.

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 with full provenance: 'Individual tax rulings of the Polish tax information office (KIS) and municipal rulings on property tax, published in the EUREKA database'. The enumerated topics (najem_prywatny, kryptowaluty, ike_ikze, etc.) make the scope concrete enough that an agent can tell this apart from rate/treaty/statistics siblings 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?

'Use for individual tax rulings by topic, for example rental income, crypto or IKE and IKZE' gives a clear selection context, and the closing line 'A ruling answers one taxpayer about their own case; it is not legal advice' sets a boundary on what the output can be used for. No explicit exclusion or named alternative tool is given, so it stops short of a 5.

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