Skip to main content
Glama

Mingpath

start_wenshi

Prepare a 问事书 (a book answering one question, with timing windows from BaZi cross-checked by Zi Wei, a month-by-month table and good dates). Returns a link to mingpath.app with the birth data and question filled in; the person reviews it there and chooses membership or a single book. Never charges. 明路会员 Mingpath Member (sku standard_*) US$69/yr founding price (list US$99) or US$9.90/mo — the price of one book, for the whole month: 2 books a month + a daily card + your life reading; 明路·同行 Mingpath Companion (sku deep_*) US$299/yr founding (list US$399) or US$29.99/mo — the whole family’s charts, updated monthly; 单本 a single 问事书 (question book) without membership US$9.90 with 3 follow-ups — see the answer to one question first; 合盘 (synastry: how two people match) US$29. Plans: 明路会员 = 2 charts, a 命书 (life reading: the full book about who you are) for each chart, 2 问事书/month, 30 follow-ups/month, a 流年书 (year book) for the primary chart before each 立春, 合盘 once a year (more at US$29 each); 明路·同行 = 5 charts, a 命书 (life reading: the full book about who you are) for each chart, 10 问事书/month, 100 follow-ups/month, a 流年书 (year book) for every chart before each 立春, monthly 流月 updates, 合盘 3 a month, priority writing. 问事书 are written in the reader's language (Simplified Chinese, Traditional Chinese or English). Follow-ups (追问) are asked on the book page with 「问这一段 / Ask about this section」 beside each section, or 「还想问什么? / What else would you like to ask?」 at the end. Auto-renews; cancel any time in one click and keep access to the end of the period. Digital content is delivered as soon as it is generated and is non-refundable. Renewal reminders are emailed before each renewal. By clicking the buy / subscribe button (「购买这一本 · US$9.90」, 「订阅明路会员 · US$69/年」…) the buyer agrees to the terms and refund policy, and the merchant of record collects its own consents at checkout. Founding prices (annual plans, 50 seats in total) are locked for life while the membership continues; GET /v1/pricing shows seats left.

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": {
      "year": "<year>",
      "month": "<month>",
      "day": "<day>",
      "template_id": "<template_id>"
    },
    "name": "start_wenshi"
  }
}

Input Schema

NameRequiredDescriptionDefault
tzNoIANA time zone of the birthplace, e.g. Asia/Shanghai, America/Los_Angeles. Preferred over tz_hours: historical summer time is applied (the mainland observed it 1986–1991, Hong Kong and Taiwan in many earlier years), so a clock time read off a birth certificate in summer time gives the right hour pillar
dayYes
hourNo0-23 local clock hour; omit if unknown
yearYes
monthYes
clientNoyour client name, e.g. claude, chatgpt, cursor (for attribution only)
genderNo
minuteNo
paramsNotemplate inputs, e.g. {"partnerGender":"female"} or {"date":"2026-12-01","action":"签约"}
zi_ruleNo子时 convention: 1 = a birth after 23:00 counts as the next day; 2 (default) = same day
tz_hoursNofixed UTC offset of the birthplace in hours, e.g. 8 (no summer time); used only when tz is absent
longitudeNobirthplace longitude in degrees east, e.g. 103.82 for Singapore
template_idYesfrom wenshi_templates

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3/5.0
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 disclose key behaviors: the tool never charges, it returns a URL where the user completes checkout, content is non-refundable digital delivery, subscriptions auto-renew and can be cancelled in one click, and founding prices are seat-limited with a pricing endpoint. That is genuinely useful for an agent explaining the handoff. It stops short of 5 because the pricing and legal boilerplate crowds out operational behavior such as what the link contains or how long generation takes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The purpose is front-loaded in the first two sentences, which is good, but the remainder is a lengthy pricing, plan-tier, renewal and refund dump that is irrelevant to invoking the tool. Every sentence should earn its place, and much of this text would be better placed in a separate pricing or help resource.

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 13-parameter, no-output-schema, no-annotation tool, the description adequately covers the deliverable shape (timing windows, month-by-month table, good dates) and the no-charge handoff flow. However it omits any guidance on obtaining template_id from wenshi_templates and on the birth-data parameters, which are the substance of the call. It is adequate but leaves real gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description says nothing about any of the 13 parameters, including required ones like template_id, year/month/day, or the meaning of zi_rule and tz. Schema coverage sits at 62%, so several parameters (year, month, day, minute, gender, client, params) are only partially documented by the schema, and the description does not compensate for that gap. It adds no meaning beyond what the schema already states.

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 opening sentence gives a specific verb and resource: it prepares a 问事书 with timing windows from BaZi cross-checked by Zi Wei, a month-by-month table and good dates, and returns a mingpath.app link with birth data and question pre-filled. That is concrete and actionable. It loses a point because it never distinguishes itself from siblings like wenshi_templates or bazi_chart, and the purpose statement is buried ahead of a very long commercial block.

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?

There is no explicit when-to-use or when-not-to-use guidance: nothing says when an agent should call start_wenshi instead of bazi_chart, ziwei_chart or request_reading. The only contextual signal is that the person reviews the result at a link and then picks a plan, which hints at the workflow but does not tell an agent how to route between tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources