get_decision

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

With no annotations, the description carries the full burden, and it does add real behavioral context: decisions are persisted to a local cache and refresh=True forces a fresh download. However, it does not say whether an uncached decision is fetched remotely (and how slow that is), what happens when the uuid/ECLI is not found, or how large the returned text can be.

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?

Three short, front-loaded lines with no filler; the purpose and identifier formats come first and the section/refresh details follow. The inline 'section: a | b | c' enumeration is compact and scannable, though the mixed Czech/English phrasing is slightly choppier than a single flowing sentence would be.

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?

An output schema exists, so return-value documentation is not needed, and the description covers all three parameters plus cache behavior. What is left thin is the failure path (invalid or unknown identifier) and the remote-fetch implications of completely uncached decisions.

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 0%, yet the description fully compensates: it explains the uuid/ECLI identifier with a concrete ECLI example, enumerates every legal value of section with Czech glosses for verdict/justification, and explains refresh's force-redownload semantics. All three parameters gain meaning beyond the bare schema.

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?

The description gives a concrete verb and resource ('Vrátí plný text rozhodnutí') plus the two accepted identifier forms (uuid or ECLI, with a worked ECLI example), which is highly specific. It never names or contrasts with siblings like search_decisions, find_by_case_number or export_decision, so the agent must infer the fetch-by-id vs. search/export split on its own.

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 only implied: an agent can infer this is the retrieval step that follows a search which produced a uuid or ECLI. There is no explicit when-to-use, no when-not-to-use, and no routing to alternatives such as export_decision or cache_search.

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