Skip to main content
Glama

Gu Search

gu_search
Read-onlyIdempotent

Search the Guam Code Annotated BY TOPIC or keyword rather than citation, "murder", "security deposit", "concealed weapon permit", "homestead". Matches against official section and chapter CATCHLINES (not full statutory body text, Guam does not publish a full-text search, and this pack derives its section catchlines from each chapter PDF's own table of contents, not a separate official index, so coverage is best-effort). Optionally filter to one Title (1-22) with title. Returns matching citations, catchlines, and title/chapter context; call gu_statute with a citation for the full text. Keyless.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "aggravated murder"
    },
    "name": "gu_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results to return, default 10, max 50.
queryYesTopic or keywords, e.g. "aggravated murder".
titleNoRestrict to one GCA Title (1-22), e.g. 9 for Crimes and Corrections.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, and openWorldHint, but the definition still adds critical context, including that matching happens against catchlines rather than statutory body text, that Guam publishes no full-text search, that catchlines are derived from chapter PDF tables of contents, and that coverage is best-effort. That sets honest expectations for recall. What's missing is pagination or truncation behavior for the limit parameter and any ordering of results, which keeps it from a 5.

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?

It leads with the core purpose and then the scope caveat, so it is front-loaded and largely earns its length. The middle sentence is an over-nested parenthetical that takes effort to parse, and the coverage caveat could be tightened without losing meaning.

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

Completeness5/5

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

For a 3-parameter search tool with no output schema, the definition covers what is returned (citations, catchlines, title and chapter context), the key limitation (catchline-only matching), the next step (gu_statute for full text), and auth (keyless). An agent has everything it needs to call it correctly and interpret the results.

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 100%, so the score starts at 3, but the definition adds real meaning by explaining that `query` matches catchlines, not body text, which materially changes how an agent should phrase queries. It also restates the Title range 1-22 and the topic-first usage, though that largely duplicates the schema.

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?

The definition names a specific verb and resource ('Search the Guam Code Annotated BY TOPIC or keyword') and explicitly contrasts itself with citation lookup, which is what gu_statute does. The example queries ('security deposit', 'concealed weapon permit') make the intended input concrete enough to separate this tool from its sibling at a glance.

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

Usage Guidelines5/5

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

It states when to use this tool (topic or keyword rather than citation) and names the complementary tool and the condition that selects it ('call gu_statute with a citation for the full text'). It also explains the optional title filter's role, so an agent knows the full call sequence, search first and then fetch the statute.

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.