Skip to main content
Glama
inboxd
by 47star

get_changes

Read durable ingestion changes, including edits and deletes, optionally filtered by source, then continue with the returned cursor to retrieve bounded message previews.

Instructions

Read durable ingestion changes, including edits/deletes, optionally scoped to one source.

Messages are bounded previews with read_request. Continue with the returned numeric cursor and the same source filter. These timestamps describe collection order, so historical backfill may appear among newly received changes. read_request retrieves the latest stored record, not a historical event version.

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
limitNo
cursorNo
sourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that messages are bounded previews, that cursor pagination must reuse the source filter, that timestamps reflect collection order so historical backfill can appear among new changes, and that read_request returns the latest stored record rather than an event version. It omits permission/auth requirements and retention behavior, keeping it below 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.

Conciseness3/5

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

The scoping and semantics are front-loaded and there is no filler, but the passage is choppy across awkward line breaks and the sentence "These timestamps describe collection order" has a dangling antecedent since no timestamps were previously introduced. The term read_request is used without definition.

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

Completeness3/5

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

For a three-parameter tool with no annotations and no output schema, the definition covers pagination, ordering caveats, and source scoping reasonably well. However, it leaves the shape of the returned preview, the limit parameter, and the meaning of read_request unexplained, which matters more heavily when no output schema exists to fill the gap.

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 0%, so the description must compensate. It gives real meaning to cursor ("the returned numeric cursor") and source ("optionally scoped to one source"), which the bare schema does not, but limit is never mentioned and the default of 50 with a maximum of 100 is left entirely to the schema's numeric bounds.

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?

"Read durable ingestion changes, including edits/deletes, optionally scoped to one source" is a specific verb plus resource with an explicit scope qualifier. It doesn't differentiate itself from siblings such as get_recent_records or search_messages, but the purpose itself is unambiguous.

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

Usage Guidelines2/5

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

The text explains how to paginate (continue with the returned numeric cursor and same source filter) but never states when to choose this tool over the alternatives. There is no exclusion, no prerequisite, and no named alternative for change-feed versus message-search use cases.

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