Skip to main content
Glama

monitor_project_history

Read-only

Poll recent project-history updates after an optional version cursor to track changes incrementally and detect gaps or earlier history.

Instructions

Poll one recent project-history window and return updates newer than an optional version cursor. In a group that starts before the cursor, only project operations at or after it are listed. Returns projectId, currentVersion (null when the window is empty), nextSinceVersion (pass it back as sinceVersion; on an empty window it repeats sinceVersion, or is null without one), hasEarlierHistory, gapDetected, and updates, newest first. Each update has fromVersion, toVersion, ISO startedAt and endedAt, authors ({ id, displayName } or null), paths, projectOperations (add, rename with newPath, remove, each with atVersion), labels, and origin ({ kind, path?, timestamp?, version? } or null).

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": {
      "projectId": "<projectId>"
    },
    "name": "monitor_project_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYesOverleaf project ID
sinceVersionNo

Output Schema

NameRequiredDescriptionDefault
updatesYes
projectIdYes
gapDetectedYes
currentVersionYes
nextSinceVersionYes
hasEarlierHistoryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral burden and does so well: window scoping, the rule that a group starting before the cursor lists only operations at or after it, null-vs-repeated cursor behavior on an empty window, and the gapDetected signal. It stops short of explaining why a gap occurs or whether a gap requires re-fetching, which would push this to 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 purpose and cursor semantics are front-loaded and useful, but the second sentence is a long enumeration of return fields that the output schema already documents. Some of it earns its place (the null/repeat rules for currentVersion and nextSinceVersion), yet a substantial portion is redundant restatement.

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 polling tool with two parameters and an output schema, the definition is close to complete: it explains the window, the cursor contract, and the ordering of results. The remaining gap is what an agent should do on gapDetected or hasEarlierHistory, and how large the 'recent window' actually is.

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 50% — projectId is documented in the schema but sinceVersion is not. The description compensates by explaining the cursor's meaning, its inclusive filtering semantics, and how to round-trip it back, which is more than the schema provides. It adds little about projectId, but the schema already covers that.

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?

The description names a specific verb and resource ('Poll one recent project-history window') and states exactly what is returned ('updates newer than an optional version cursor'). No sibling in the catalog covers project history, so the tool is naturally differentiated, but the description never explicitly contrasts itself with any alternative tool.

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?

It conveys the core polling loop ('nextSinceVersion, pass it back as sinceVersion') and clarifies the empty-window edge case, which is genuine usage guidance. However, there is no when-to-use/when-not guidance, no advice on how to react to gapDetected or hasEarlierHistory, and no mention of polling frequency limits.

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