search_cases

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

With no annotations, the description fully bears the burden of behavioral disclosure. It transparently states that win_rate is always null and n_cases is capped at 2000 with a flag. It also clarifies that results include body_excerpt but not full text. These are important limitations that are clearly communicated.

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 verbose but efficiently packs essential information. It starts with the core function, then lists features, caveats, and sibling tool references. Some redundancy exists (e.g., the stats caveats are repeated), but every sentence contributes to understanding. Could be slightly more concise, but structure is good.

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?

Given the tool's complexity (8 parameters, mixed search, important caveats, sibling tools), the description is complete. It explains return values (similarity, percentiles, factors), output limitations (no full text), and edge cases (capped n_cases, null win_rate). Without an output schema, it adequately covers the return structure.

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. The description does not add significant meaning beyond the schema; it provides an example query for the 'q' parameter but otherwise the schema already documents each parameter thoroughly. The description's mention of 'mixed search' is helpful but not additional semantic detail.

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 clearly states the tool retrieves Chinese labor dispute judgments (110万+ structured cases) and returns high similarity cases, amount percentiles, and key adjudicative factors. It explicitly distinguishes itself from siblings by indicating what it does not return (full text) and directing users to other tools for that purpose.

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?

The description provides detailed guidance on when to use this tool (for case summaries, stats, and links) and when not to (for full judgments, use search_judgments_full or browse_full_corpus). It also includes critical caveats about win_rate being null and n_cases capping at 2000, preventing misuse.

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