Skip to main content
Glama

Veyrul media knowledge hub

Get changes since a cursor

get_changes
Read-only

Events (records, replies, claims, submissions, reviews) after since, optionally per project_id/record_id. Save next_cursor; pass it as since next session.

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
limitNoMaximum number of results within the documented per-tool range.
sinceNoOpaque next_cursor returned by get_changes. Omit to begin the public event feed.
record_idNoOptional permanent record ID to restrict public change events.
project_idNoOptional permanent project ID to restrict results.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of results within the documented per-tool range."
    • addedInput schema / properties / project_id / description
      Added value: +"Optional permanent project ID to restrict results."
    • addedInput schema / properties / record_id / description
      Added value: +"Optional permanent record ID to restrict public change events."
    • addedInput schema / properties / since / description
      Added value: +"Opaque next_cursor returned by get_changes. Omit to begin the public event feed."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly/non-destructive/closed-world, so the description is free to add the thing that actually matters: the response carries a `next_cursor` that must be persisted to continue the feed. That is a real behavioral contract disclosed with no output schema present. It stops short of stating what happens at end-of-feed, ordering guarantees, or limit interaction.

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?

Two short sentences, zero filler: content of the feed first, scoping second, pagination instruction last. Every clause carries weight and nothing is buried.

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?

With no output schema, the description correctly surfaces the one return field an agent cannot proceed without (next_cursor). For a 4-param, zero-required, read-only polling tool this is close to sufficient; only feed termination and ordering behavior are left unstated.

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 description coverage is 100% — `since` is already documented as an opaque cursor and project_id/record_id as filters — so the baseline applies. The description restates the same semantics ("after `since`", "optionally per project_id/record_id") without adding format, interaction, or precedence rules between the two filters.

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?

Names the resource precisely — an event feed — and enumerates the event types it carries (records, replies, claims, submissions, reviews), plus the optional scoping dimensions. It does not distinguish itself from the nearby sibling `collaboration_changes`, which appears to be a parallel change-feed tool, so an agent must infer the boundary.

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?

Gives a concrete polling workflow ("Save next_cursor; pass it as since next session"), which is genuinely actionable, but never states when to choose this over `collaboration_changes` or `search`, nor any exclusion. Usage is implied by the cursor mechanics rather than argued.

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