Skip to main content
Glama

Search Indiana cases

case_search
Read-onlyIdempotent

Search Indiana Supreme Court, Court of Appeals, and Tax Court clusters from a CourtListener extract. court is ind, indctapp, or indtc. form is memorandum or opinion when decision forms are indexed (text classification, not official status). disposition is affirmed, reversed, remanded, vacated, dismissed, mixed, or unlabeled when that index is loaded. A single label also matches a mixed closing that includes it. The label is a rule read of the closing line, not an official judgment. standard is de_novo, abuse_of_discretion, clearly_erroneous, sufficiency, prima_facie_error, substantial_evidence, or arbitrary_or_capricious when that index is loaded. Plain words such as 'de novo' are accepted. A standard is a rule read of a sentence that states it, not a ruling on which standard governs. separate is concurs, dissents, concurs_in_part, dissents_in_part, concurs_in_result, transfer_dissent, or joins when that index is loaded. That label is the slip's own "with separate opinion" vote line, not a holding. author is the slip byline name, or per_curiam, when that index is loaded. Most hits are metadata only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "case_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
formNo
afterNo
courtNo
limitNo
queryYes
authorNo
beforeNo
offsetNo
separateNo
standardNo
dispositionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "title": "Offset",
      +  "type": "integer"
      +}
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still earns credit for disclosing that labels are heuristic rule-reads rather than official status ('text classification, not official status', 'not an official judgment', 'not a holding') and that 'Most hits are metadata only' — meaningful caveats an agent would otherwise misread. It omits ranking, pagination, and what a metadata-only hit actually contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and every sentence carries real information, but the whole thing is one unstructured block of near-identical 'X is ... when that index is loaded' sentences. A short bulleted list per filter, or grouping the shared 'index may not be loaded' caveat once, would scan far faster.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value documentation is not required. However, for an 11-parameter search tool the description leaves the required query parameter and the date-range parameters undefined, which are the gaps an agent is most likely to trip on.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage and 11 parameters, the description must carry the load. It thoroughly documents court, form, disposition, standard, separate, and author, including accepted plain-word forms, but leaves query (the only required parameter) completely unexplained — no syntax guidance for CourtListener query language — and never covers after/before date formats or limit/offset paging.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource set: search Indiana Supreme Court, Court of Appeals, and Tax Court clusters from a CourtListener extract. That is clearly distinct from code-oriented siblings like ic_search or iac_search, though it never names a sibling to route against (case_get, cases_citing_case).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what each filter value means but never says when to use this tool versus case_get (fetch a known case), cases_citing_case (citation graph), or ic_search (statute text). No prerequisites, no exclusions, no mention of when a filter combination is inappropriate.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.