Skip to main content
Glama
Ancient Echoes MCP

Ancient Echoes MCP

Entrepreneurship Context

bazi.analyze_entrepreneurship
Read-only

Turns BaZi career-wealth evidence, target year, and user constraints into startup decision support, returning starting conditions and text-matched business candidates without scores or rankings.

Instructions

把当前用户命盘的事业财运结构证据、显式目标年份和用户填写的职业/资源/约束分层整理为创业决策辅助;返回无评分、无排名的起步结构条件与仅由用户文本命中的业务候选,不根据命盘裁决公司形态、赛道、城市或成功率。

Input Schema

NameRequiredDescriptionDefault
contextYes
record_idNo
target_yearYes
use_profileNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.6/5.0
Behavior4/5

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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower; the description still adds real behavioral context by declaring the output is 无评分、无排名 and that business candidates are hit only by user text rather than derived from the chart. The explicit refusal to decide 公司形态、赛道、城市、成功率 is exactly the kind of scope boundary an agent needs before presenting results. It does not, however, disclose how the chart-vs-profile branch changes the behavior.

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?

One dense sentence chain that front-loads what is compiled and then what is refused; the semicolon split keeps the output shape and the negative scope readable. Nothing is filler, though the sentence is long enough that the two constraints (no scoring, no verdict on company form/track/city) blur together.

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 tool with a nested context object, a mutually exclusive input branch, zero schema coverage and no output schema, the description does cover the conceptual model and the non-evaluative nature of the return. It leaves a real gap on how to choose record_id versus use_profile and on which of the nine context subfields actually matter, so an agent could still call it wrongly.

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 0%, so the description has to carry the load. It does add meaning for target_year (must be explicitly supplied, not inferred) and for the context object (profession, resources, constraints supplied by the user and layered as text), but it never explains the oneOf between record_id and use_profile, which is the single most consequential parameter decision in this schema.

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 concrete verb and resource set: it organizes 命盘事业财运结构证据, 显式目标年份 and 用户填写的职业/资源/约束 into 创业决策辅助, and it states what the output is (起步结构条件与业务候选). That is far more specific than the title, but it never distinguishes itself from the closest sibling bazi.analyze_wealth, which also covers career/wealth structure.

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?

Usage is implied by the framing: bring chart evidence plus an explicit target year plus user-supplied profession/resource/constraint text when the user wants entrepreneurship decision support. The exclusions are stated (it will not adjudicate 公司形态、赛道、城市或成功率), which usefully bounds expectations, but no sibling alternative is named and no precondition (e.g. chart must already exist, or use_profile vs record_id) is given.

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