Indiana Code

Search the Indiana Administrative Code

iac_search

Read-onlyIdempotent

Full-text search of the electronic Indiana Administrative Code. year is an edition year such as 2006; omit it to use the edition iar.iga.in.gov labels Current. Returns section ids, headings and snippets; fetch text with iac_get_section. title is an IAC title number such as '10' or '312'. Unofficial; not legal advice. Verify at iar.iga.in.gov.

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": "iac_search"
  }
}

Input Schema

Name	Required	Description	Default
`year`	No
`limit`	No
`query`	Yes
`title`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds real value: results are snippets not full text, the tool is unofficial and not legal advice, and year omission silently defaults to the Current edition.

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

Conciseness4/5

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

Every sentence carries information with no filler, but the ordering is choppy—year semantics appear before query/title basics, and the disclaimer trails awkwardly. Front-loading the search purpose and core params first would improve it.

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

Completeness4/5

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

For a filtered search tool with an output schema and strong annotations, it covers nearly everything an agent needs: scope, snippet-vs-full-text behavior, year defaulting, and the fetch follow-up. Minor gaps are the unexplained limit param and no guidance on iac_browse vs this tool.

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

Parameters4/5

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

Schema coverage is 0%, so the description must carry parameter meaning, and it explains the two non-obvious params: year as an edition year with a Current default, and title as an IAC title number with examples. Only 'limit' is left unexplained (though its default hints at pagination behavior).

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

Purpose5/5

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

States a specific verb+resource ('Full-text search of the electronic Indiana Administrative Code') and explicitly routes results-fetching to the sibling iac_get_section. An agent can tell it apart from iac_get_section and iac_browse without opening schemas.

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

Usage Guidelines4/5

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

Gives concrete usage: omit year to use the Current edition, and use iac_get_section to fetch full text after searching. Does not distinguish when to use this vs iac_browse or ic_search (Indiana Code), so sibling selection beyond iac_get_section is left to inference.

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

All Indiana Code tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.