Skip to main content
Glama

extract_foreshadow

Extracts foreshadowing candidates from novel text without LLM tagging, identifying suspense or unfinished events so writers can review them before registering a ledger entry.

Instructions

【零 LLM】从正文通用抽取伏笔候选(无 F# 编号也能识别悬念/未完成事件),供登记台账前参考。

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": {
      "text": "<text>"
    },
    "name": "extract_foreshadow"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It adds real value by declaring 【零 LLM】 (zero LLM calls, so the extraction is rule-based, cheap and deterministic) and by clarifying that F# numbering is unnecessary because the tool tolerates unregistered entities; however, it says nothing about the result format, confidence, or whether candidates are deduplicated.

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 whole description is one bracketed, front-loaded sentence with the decisive qualifier 【零 LLM】 first and the workflow hint last; nothing is padded. The mixed bracketing and parentheses are slightly noisy but do not obscure the content.

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 simple one-parameter extraction tool, no output schema, the description covers the input and the purpose but leaves the return shape unstated: whether the output is a list of candidate strings, scored items, or excerpts. An agent knows what to send but not what it will get back.

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?

There is only one parameter, and its schema has 0% description coverage, yet the name 'text' is largely self-explanatory and 从正文 ("from the body text") confirms that the input is the manuscript prose rather than an outline or metadata. That is about as much as the single parameter needs.

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 states a specific verb and resource — generically extracting foreshadowing (伏笔) candidates from body text — and narrows the scope by noting it identifies suspense or unfinished events even without an F# number, which distinguishes it from the ledger-registration siblings like add_foreshadow and foreshadow_list. It stops short of naming a sibling explicitly, so it does not fully separate itself from extract_facts.

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?

The clause 供登记台账前参考 ("for reference before registering in the ledger") implies a workflow position, namely use this before add_foreshadow, but the ordering is left implicit and there is no statement of when not to use the tool or how it compares with extract_facts.

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