get_citations

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the two operating modes and what include_context does (80-character surrounding snippet), which is real behavioral value, but says nothing about return structure, pagination, or error/empty cases.

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 the resource, then the two direction modes, then the alternative tool, then the args. Each sentence earns its place and the layout is easy to scan, though the arg block partially restates schema entries.

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?

With no annotations and no output schema and 3 parameters, the description covers the necessary ground: what it returns in each direction, all parameter meanings, and the routing to a sibling. Only finer detail about return formatting is absent, which the directions largely imply.

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%, so the description must compensate, and it documents all three params: case_id (format matching get_interpretation), include_context (attaches ~80 chars of source text), and direction with both allowed values explained. This adds clear meaning beyond the bare schema, though case_id format is only referenced indirectly via another tool.

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 names the specific resource (citation relationships between 大法官解釋/憲判字) and the specific operation for each direction, clearly stating the verb+resource. It explicitly distinguishes itself from the sibling search_judgments and names it, letting an agent tell the two apart without opening a 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?

It states precisely when to use each mode: direction="cites" for backward tracing from the reasoning text, direction="cited_by" for forward tracing from later texts. It also names the alternative (search_judgments) with the exact condition and keyword format for choosing it, leaving nothing to inference.

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