Skip to main content
Glama

novel_diagnose

Diagnoses a novel library and data directory health by reading logs and generating metadata-only reports; also lists events or clears logs.

Instructions

诊断报告:读日志体检书库与数据目录(只含元数据,不含正文)。

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": "novel_diagnose"
  }
}

Input Schema

NameRequiredDescriptionDefault
bookNo按书过滤
daysNo天数(7)
rootNo书库根
actionNoreport/events/clear

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv8.0.0
    • changedInput schema / properties / action / description
      Previous value: -"report=生成报告(默认);events=附带事件明细(≤200 条);clear=清空本地事件日志。"New value: +"report/events/clear"
    • changedInput schema / properties / book / description
      Previous value: -"可选。只看这本书相关的事件(按事件里的书名过滤)。"New value: +"按书过滤"
    • changedInput schema / properties / days / description
      Previous value: -"统计窗口(天),默认 7,上限 90。"New value: +"天数(7)"
    • changedInput schema / properties / root / description
      Previous value: -"章节库根目录(含 novels 子目录)。"New value: +"书库根"
  2. Addedv6.6.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that output is metadata-only and excludes body text, which is real added context. However, it never mentions the 'clear' action, which strongly implies destructive log removal, so an agent reading only this text would assume a purely read-only diagnostic tool — a material omission.

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?

A single front-loaded sentence: the purpose label comes first, followed by the mechanism and the important metadata-only constraint. Nothing is padded, though the brevity comes at the cost of omitting the action modes entirely.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Four parameters including a three-value enum with a likely destructive 'clear' branch, no annotations, and no output schema. The description neither explains what a report or events dump contains nor warns about clearing data, so it is well short of what an agent needs to call all modes safely.

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%, so every parameter is already documented in the schema, including the action enum. The description adds only the implicit mapping of 'logs' and 'data directory' onto the root parameter, which is marginal. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific operation: reads logs and performs a health check on the library and data directory, with the scope qualifier that only metadata is involved, never manuscript text. This distinguishes it reasonably from content-oriented siblings like novel_read or novel_style_check, though the headline framing 'diagnostic report' understates the tool's full action surface.

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?

No guidance on when to reach for this versus alternatives such as novel_continuity_check or novel_style_report, and no prerequisites or preconditions are given. The 'action' values (report/events/clear) are never discussed, so the agent gets no cue about which mode fits which situation.

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