Find the judgment(s) at an exact law-report citation.
Example: journal='PLD', year=1995, page=34 → PLD 1995 Supreme Court 34.
Omit page to list everything reported in that journal+year. Returns the same case shape
as caselaw_search.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses that omitting page returns a full list for that journal+year, and that the return shape matches caselaw_search. This adds meaningful behavioral context not present in 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?
The description is three sentences plus a compact example. It front-loads the purpose, uses the example to illustrate parameters, and includes no redundant text. Every sentence earns its place.
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?
The description covers the core lookup, the list-vs-single behavior, and references caselaw_search for the return shape. Pagination (limit/offset) and response_format are defined in the schema, so their absence from the description is acceptable. It is complete for a read-only citation lookup tool.
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?
The example directly maps journal='PLD', year=1995, page=34 to a concrete citation, clarifying how the primary parameters interact. It also explains the semantic effect of omitting page (list all cases), which is not obvious from the schema alone. This compensates for the sparse schema descriptions.
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 begins with a clear, specific verb and resource: 'Find the judgment(s) at an exact law-report citation.' This distinguishes the tool from siblings like caselaw_search (keyword search) and caselaw_get_case (by ID) by focusing on exact citation lookup.
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 example with journal/year/page and the note 'Omit page to list everything reported in that journal+year' give clear context for when to use the tool. It does not explicitly exclude sibling tools, but the mention of 'Returns the same case shape as caselaw_search' provides a useful consistency reference without being an explicit alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: fetching a case by ID, searching full-text, resolving a citation, traversing the citation graph forward or backward, and listing landmark cases. There is no overlap or ambiguity between them.
All tools share the caselaw_ prefix and mostly follow a verb-first pattern (get_case, get_citations, get_cited_by, lookup_citation, search). The exception is caselaw_most_cited, which uses an adjective phrase rather than a verb, causing a minor inconsistency.
Six tools is well-scoped for a legal research server. Each tool covers a necessary part of the workflow without redundancy or bloat.
The read-only domain of case law research is well covered: search, retrieval, citation lookup, and both directions of citation traversal are present. The landmark listing provides an entry point, and there are no obvious dead ends in the research flow.