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

With no annotations, the description carries the full burden of behavioral disclosure. It states that judgment content is not saved, results are sorted by court level, each entry contains specific fields, and explains JID deduplication behavior. This is rich contextual detail beyond the schema.

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?

The description is front-loaded with purpose and every clause contributes value, but it runs as one dense paragraph. It could be more scannable with structured formatting (e.g., bullets), but it is not verbose or 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?

Despite no output schema, the description specifies result fields, sorting order, and usage patterns for different search modes (case number, main_text, query, semantic merge). It sufficiently covers the complexity of a 9-parameter search tool with 0 required parameters.

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 78%, but the description adds substantial meaning beyond field descriptions: a concrete example for case_word/case_number/year_from, example mapping of main_text phrases to winners/losers, and the note that main_text can be combined with query. This goes well beyond the baseline.

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?

Description clearly states it uses the Judicial Yuan judgment system to search public judgments, with a specific verb and resource. It distinguishes itself from siblings by describing result sorting by court level and the fields included, making it clear this is a search tool rather than a retrieval or interpretation tool.

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?

Provides explicit usage guidance: how to search a specific case number using case_word, case_number, and year_from, and to avoid putting the case number in query. It also explains main_text usage for filtering winners/losers and recommends merging with semantic search tools using JID, explicitly warning that results without JID should not be cited. This qualifies as explicit when/when-not guidance with alternatives.

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