Skip to main content
Glama

What changed since

get_changes
Read-onlyIdempotent

What changed in Georgia Commons since a cursor or a moment, oldest first: documents first loaded (created), new text (text_changed: a new bill version, minutes a body replaced), a bill's new actions and status (status_changed, with the actions and the status before and after), other record changes, and withdrawals. For tracking on a schedule: keep next_since and pass it as since next time, and nothing is missed or repeated. The clock is Georgia Commons' own (when it loaded or changed a document), never the document's date.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoOnly one document's events: its id or any written form (HB 340).
bodyNoOnly these issuing bodies, by id.
kindNoOnly these kinds of change.
limitNoEvents to return: 1 to 200.
placeNoOnly the documents of one place's own governments: a place in words or as an id (Marietta, city:savannah).
sinceNoWhere to start: the next_since of your last call, a date or an ISO 8601 date and time, or `now` (nothing yet, only a cursor to start from). Omit for the feed's first events.
collectionNoOnly these collections.

Output Schema

NameRequiredDescriptionDefault
noteNo
eventsNo
caught_upYesFalse: more events are waiting after next_since.
truncatedNo
next_sinceYesPass as `since` on the next call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds substantial behavior: result ordering, cursor guarantees ('nothing is missed or repeated'), and the critical clock semantics ('Georgia Commons' own clock, never the document's date'). It also clarifies that text_changed covers replaced minutes, not just new bill versions, which an agent could not infer from the enum alone.

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?

Four sentences, front-loaded with purpose, then event taxonomy, then the scheduling loop, then the clock caveat. Dense but every sentence carries information an agent needs; the parentheticals are long but not redundant. Slightly heavy for a single paragraph, though nothing is filler.

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?

An output schema exists, so return shape needn't be described, and the description covers the remaining agent-critical unknowns: ordering, cursor continuity, clock source, and the meaning of each change kind. For a 7-parameter, no-required-parameter feed tool, nothing material is left ambiguous.

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 baseline is 3, but the description adds real meaning: it ties `since` to the `next_since` of a prior call and the `now` start case as a cursor bootstrap, and it explains what `text_changed` and `status_changed` actually contain (before/after status and actions). That goes beyond the parameter descriptions in 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 description opens with a specific verb-and-resource statement ('What changed in Georgia Commons since a cursor or a moment') and then enumerates the exact event kinds returned (created, text_changed, status_changed, record_changed, withdrawn). This is a change-feed, clearly distinct from the sibling search/fetch/verify_quote tools, and the 'oldest first' ordering is stated up front.

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?

It gives an explicit usage pattern for the main scenario: 'For tracking on a schedule: keep next_since and pass it as since next time.' That tells the agent both when to use the tool and how to chain calls. It stops short of naming a sibling alternative or an exclusion (e.g., use search for one-off lookups), so it is clear context without explicit routing.

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.

Resources