Skip to main content
Glama
story-architect-mcp

story-architect-mcp

by PTCuong-1102

Prune Old Snapshots

story_prune_snapshots

Prune old full-copy snapshots to reduce disk bloat: preview deletions first, then keep the newest N while safeguarding recent backups.

Instructions

Dọn dẹp các snapshot cũ trong .story/snapshots/ (mỗi snapshot là full-copy nên dễ phình đĩa). Giữ lại N snapshot mới nhất; dry-run preview trước khi confirm. Snapshot mới nhất và backup pre-rollback gần đây luôn an toàn vị trí — chỉ bị xóa khi vượt ngưỡng được chọn.

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": "story_prune_snapshots"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNofalse = chỉ xem preview, true = thực hiện xóa
keepLastNoSố snapshot MỚI NHẤT luôn giữ lại (kể cả khi vượt olderThanDays)
olderThanDaysNoChỉ xóa snapshot cũ hơn số ngày này (bỏ trống = xóa mọi snapshot ngoài keepLast)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does a good job: it discloses that this is a destructive delete of on-disk snapshots, that confirm=false means preview-only, and that the newest snapshot plus recent pre-rollback backups are protected unless thresholds are exceeded. It stops short of stating irreversibility or what exactly the preview reports.

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?

Three tight sentences with the resource/risk front-loaded and the safety guarantee last; nearly every clause earns its place, though the disk-bloat rationale could be trimmed.

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 destructive, zero-annotation tool with no output schema, the description covers purpose, default-safe behavior, and retention guarantees. It leaves minor gaps around what the dry-run preview returns and whether deletion is reversible.

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% and each parameter is already documented, so the schema does the heavy lifting. The description paraphrases keepLast and the confirm/dry-run behavior, adding minimal information beyond the structured fields.

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 a specific verb+resource (prune old snapshots in .story/snapshots/) and explains the reason (full-copy snapshots bloat disk). It does not explicitly name story_snapshot or story_rollback as the create/restore counterparts, so sibling differentiation is implied via the pre-rollback backup mention rather than stated.

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?

Clearly frames the workflow: default dry-run preview, then confirm=true to actually delete, and retain the N most recent. It gives safe-usage context but no explicit 'do not use when' exclusions or pointers to alternatives.

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