get_judgment

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

No annotations are provided, so the description carries the full burden and does substantial work: it enumerates the returned fields, explains the history/history_note structure, and warns about overturning risk. Gaps remain on error behavior (e.g., what happens if both jid and url are empty) and permissions.

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-loads the one-line purpose, then structures the two query modes and the return contract. Every section earns its place given the empty schema, though the Args/Returns blocks are somewhat verbose.

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 retrieval tool with no output schema and no annotations, the description supplies both the output field list and behavioral caveats (history checking). The remaining gap is the required/precedence semantics of jid vs url.

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 0% (bare string fields with default ''), so the description must compensate and does: it gives a concrete JID example with format ('TPSV,104,台上,472,20150326,1') sourced from search results, and a URL example. It does not state whether one parameter is required or which wins when both are supplied.

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: '取得單一裁判書全文' (retrieve full text of a single judgment). This is unambiguous and clearly distinguishes it from search-family siblings like search_judgments.

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 lays out the two query modes (JID vs URL) with the source system for each, and adds real usage advice: check history before citing because a later instance-level judgment may have overturned or remanded this one. It does not, however, say when to reach for this over get_precedent or after search_judgments.

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