Skip to main content
Glama

search_bills

Read-only

Search Utah Legislature bills by keyword across titles, subjects, and summaries, or filter by session, sponsor, status, and subject to list matching bills.

Instructions

Keyword search over bill titles, subjects and summaries for a session. With an empty query, lists bills matching the subject/sponsor/status filters. The first search of a session starts building a local index in the background (~10 min, rate-limited); until it finishes, results cover passed bills (titles only) plus whatever has been indexed so far.

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": "search_bills"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax items to return (1-50).
queryYesKeywords matched against titles, subjects and summaries.
offsetNoStart position for paging; use next_offset from a prior call.
statusNoOnly bills whose last action contains this, e.g. 'Governor Signed'.
sessionNoSession, e.g. '2026', '2026GS', '2025S1'. Omit for the current general session.
sponsorNoOnly bills whose sponsor/floor sponsor name contains this.
subjectNoOnly bills with a subject containing this text.
max_charsNoCharacter budget for this response (500-20000). Defaults to the server setting.
include_requestsNoAlso match unnumbered bill requests by title.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Adds substantial behavior beyond readOnlyHint/openWorldHint: first search of a session kicks off a ~10 minute background index build, the call is rate-limited, and until indexing completes results are limited to passed bills with titles only. This is exactly the kind of degraded-result and latency disclosure an agent needs. It stops short of stating what a fully indexed result contains or how to tell indexing has finished.

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

Conciseness5/5

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

Three sentences, each carrying distinct information: search scope, empty-query behavior, and index warm-up caveats. Front-loaded with the primary purpose and no wasted phrasing.

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 9-parameter read-only search with no output schema, the description covers the two things the schema cannot: query semantics and the indexing latency/partial-results constraint. Return shape and pagination are left to the schema (next_offset is referenced there), which is acceptable.

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?

Schema coverage is 100%, so the parameters are already documented. The description adds only the interaction rule that an empty query plus subject/sponsor/status filters yields a filtered list, which is marginally more than the schema states, but it says nothing about limit/offset/max_chars beyond what the schema covers.

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?

States a specific verb (keyword search) over specific fields (titles, subjects, summaries) scoped to a session, and clarifies that an empty query degrades into a filtered listing. This distinguishes it in spirit from the list_* siblings, though no sibling is named.

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

Usage Guidelines3/5

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

The empty-query case is explicitly described, which is genuine when-to-use guidance. However, there is no explicit routing against alternatives like list_bills or get_bill, and the index warm-up is framed as a caveat rather than telling the agent when to refresh first or fall back to another tool.

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