Skip to main content
Glama

chronica_summarize

Generate time-based summaries from structured memory data for daily, weekly, or decision-focused review periods.

Instructions

サマリーパックを生成します(Summary Pack v0.1.2)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYesモード
range_startYes範囲開始時刻(ISO文字列、JST)
range_endYes範囲終了時刻(ISO文字列、JST)
thread_typeYesスレッドタイプ

Implementation Reference

  • The tool handler logic for 'chronica_summarize' which parses arguments and calls the 'summarize' function.
    elif name == "chronica_summarize":
        mode = arguments.get("mode")
        range_start = arguments.get("range_start")
        range_end = arguments.get("range_end")
        thread_type = arguments.get("thread_type")
        
        if not all([mode, range_start, range_end, thread_type]):
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "invalid_range", "message": "mode, range_start, range_end, and thread_type are required"}, ensure_ascii=False)
            )]
        
        if mode not in ["daily", "weekly", "decision"]:
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "invalid_range", "message": f"mode must be 'daily', 'weekly', or 'decision', got: {mode}"}, ensure_ascii=False)
            )]
        
        if thread_type not in ["normal", "project"]:
            return [types.TextContent(
                type="text",
                text=json.dumps({"error": "invalid_thread", "message": f"thread_type must be 'normal' or 'project', got: {thread_type}"}, ensure_ascii=False)
            )]
        
        summary_pack = summarize(
            mode=mode,
            range_start=range_start,
            range_end=range_end,
            thread_type=thread_type,
            store=store
        )
        return [types.TextContent(
            type="text",
            text=json.dumps(summary_pack, ensure_ascii=False, indent=2)
        )]
  • The actual implementation of the 'summarize' function, which processes entries from the store.
    def summarize(
        mode: str,
        range_start: str,
        range_end: str,
        thread_type: str,
        store: Store
    ) -> Dict[str, Any]:
        """サマリーパックを生成"""
        entries = store.timeline(
            start_time=range_start,
            end_time=range_end,
            thread_type=thread_type
        )
        
        stats = {
            "total_entries": len(entries),
            "by_kind": {}
        }
        for entry in entries:
            kind = entry.get("kind", "unknown")
            stats["by_kind"][kind] = stats["by_kind"].get(kind, 0) + 1
        
        timeline_items = []
  • The registration and schema definition of the 'chronica_summarize' tool.
    types.Tool(
        name="chronica_summarize",
        description="サマリーパックを生成します(Summary Pack v0.1.2)。",
        inputSchema={
            "type": "object",
            "properties": {
                "mode": {
                    "type": "string",
                    "enum": ["daily", "weekly", "decision"],
                    "description": "モード"
                },
                "range_start": {
                    "type": "string",
                    "description": "範囲開始時刻(ISO文字列、JST)"
                },
                "range_end": {
                    "type": "string",
                    "description": "範囲終了時刻(ISO文字列、JST)"
                },
                "thread_type": {
                    "type": "string",
                    "enum": ["normal", "project"],
                    "description": "スレッドタイプ"
                }
            },
            "required": ["mode", "range_start", "range_end", "thread_type"]
        }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but it fails to indicate whether this is a read-only analysis operation or if it persists data. It does not describe output format, size limits, or computational cost despite the lack of an output schema.

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 description is a single sentence and appropriately brief, but includes the version number 'v0.1.2' which is noise for an AI agent selecting tools. The core message is front-loaded but lacks density of useful information.

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

Completeness2/5

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

Given 4 required parameters with specific enum values (daily/weekly/decision, normal/project) and no output schema, the description is insufficient. It fails to explain what distinguishes the three modes or thread types, and provides no indication of the return value structure or content.

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?

The input schema has 100% description coverage with Japanese labels explaining each field (e.g., '範囲開始時刻'). The description adds no additional semantic context beyond the schema, but baseline 3 is appropriate given the schema's completeness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the basic action (generate/create) and resource (summary pack), but 'Summary Pack' is not defined, leaving ambiguity about the output format and content. It does not differentiate from siblings like chronica_timeline or chronica_search that also provide aggregated views of data.

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

Usage Guidelines1/5

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

No guidance is provided on when to use this tool versus alternatives (e.g., when to use 'decision' mode vs regular search, or when chronica_timeline is more appropriate). No prerequisites or exclusion criteria are mentioned.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nic9dev/Chronica'

If you have feedback or need assistance with the MCP directory API, please join our Discord server