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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is established. The description adds non-redundant behavioral context: it names the data source ('Caselaw Access Project, public domain'), clarifies that results are metadata (not full opinions), and discloses the U.S. Reports index limitation. There is no contradiction with the annotations.

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 tight sentences: the first states the core purpose, the second states the return value and next step, and the third adds an essential scope caveat. Every sentence earns its place, and the key search semantics are front-loaded.

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 6-parameter, no-output-schema search tool, the description covers the essential facts: what is searched, what is returned, how to obtain the full text, and the critical index limitation. It does not describe output formatting or ordering, but the absence of an output schema makes the metadata/citation mention particularly valuable. A small gap is the lack of guidance on how this differs from other court-search siblings like court_opinion_search.

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 100%, so the input schema fully documents all six parameters. The description loosely mirrors these by mentioning 'case name / keyword, court, jurisdiction, and decision-date range', but adds no syntax, defaults, or format details beyond the schema. Baseline 3 is appropriate because the description does not need to compensate for schema gaps.

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 starts with a specific verb and resource: 'Search US court opinions', then enumerates the filter dimensions (case name/keyword, court, jurisdiction, decision-date range). It also states the output shape ('matching case metadata with CAP ids and citations'), which clearly distinguishes it from caselaw_opinion_text, the sibling that retrieves full text. The v1 index note further disambiguates scope from other court-search tools in the sibling list.

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 gives a clear follow-up instruction: 'Use caselaw_opinion_text with a returned id to read the full opinion,' which routes the agent to the correct sibling for the next step. It also discloses a meaningful limitation ('v1 index covers the U.S. Reports reporter'), implying when the tool may not be appropriate. However, it does not explicitly compare against other caselaw siblings such as caselaw_case_details or caselaw_citation_lookup, nor state when not to use this tool.

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