Skip to main content
Glama

semester_sync

Downloads and organizes semester course materials, assignment and announcement attachments into course-based folders, then generates overview README and per-course info files for easy review.

Instructions

整理学期资料:把每门课的资料、作业附件、公告附件下载到本机,按「课程/资料|作业|公告/条目」分文件夹, 并生成学期总览 README.md 和每门课的 课程信息.md(上课时间地点、考试、作业截止与状态、公告、资料索引)。

dest 默认 ~/PKU/<学期名>。可反复调用,只补新文件,不覆盖、不删除已有文件;超过 max_file_mb 的文件跳过并列出。
单次调用约 45 秒,返回 done=false 时用相同参数再调用,直到 done=true。course_id 只整理一门课。

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": "semester_sync"
  }
}

Input Schema

NameRequiredDescriptionDefault
destNo
course_idNo
max_file_mbNo
include_hiddenNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full load, and it does well: it discloses non-destructive semantics (no overwrite, no delete), the skip-and-report behavior for files over max_file_mb, an approximate 45-second runtime, and the done=false continuation pattern. It does not mention authentication requirements or what happens on partial failure, which keeps it from 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.

Conciseness4/5

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

The description is front-loaded with the core action and output layout, then moves to defaults, idempotency, timing and the polling rule. Every sentence carries operational information, though the density is high and the folder-path notation plus generated filenames make the opening block slightly heavy.

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 bulk, long-running sync tool with an output schema available, the description covers the workflow, output artifacts, resumability and file-size policy — enough to call it correctly. The main gap is the absence of any auth prerequisite note, notable given auth_setup and auth_status exist among the siblings.

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 0%, so the description must compensate, and it explains three of the four parameters meaningfully: dest defaults to ~/PKU/<semester name>, course_id narrows to one course, and max_file_mb controls skipping with the skipped files listed. include_hidden is never mentioned, leaving one undocumented parameter.

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

Purpose5/5

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

The description states a specific verb and resource set: download all course materials, assignment attachments and announcement attachments to the local machine, organized into course/type/item folders, plus generated README.md and 课程信息.md summaries. This is clearly distinguishable from siblings like attachment_download or content_list, which fetch individual items rather than performing a whole-semester local sync.

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?

The description gives explicit operating guidance: it can be called repeatedly, it only fills in new files, and course_id limits the sync to a single course. It also gives a clear polling rule — repeat with the same parameters while done=false. What is missing is when not to use it versus the per-item siblings, and any prerequisite such as authentication.

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