Skip to main content
Glama

check_ai_flavor

Audits chapter text for AI-flavored wording, oily phrasing, repetitive sentence patterns, and forced endings, then returns a problem list with exact locations.

Instructions

【执行层/质检层】AI 味审计:红牌词(≤1/章)、油腻词(一票否决)、句式(不是A而是B ≤2、这,就是 ≤1)、段末升华检测。输出问题清单+具体位置。

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": "check_ai_flavor"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes章节正文
project_idNo

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?

There are no annotations, so the description bears the full disclosure burden. It does useful work: it discloses the pass/fail semantics (油腻词 'one-vote veto'), the per-chapter threshold for red-card words, and that the return is a problem list with specific locations. It does not state that the operation is read-only and non-mutating, nor what happens when thresholds are exceeded beyond a veto, leaving an audit-shaped mutation question unanswered.

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 definition is essentially one compressed line that front-loads the audit purpose and then the rule set and output, with no filler. The dense threshold shorthand (≤1/章, ≤2, ≤1) is efficient for a reader who knows the domain, though an unfamiliar agent must parse symbols before reaching the core claim.

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?

With no annotations and no output schema, the description is the sole source of behavioral detail, and it supplies both detection rules and the shape of the result (problem list plus locations). The remaining gap is the undocumented project_id parameter and the absence of any statement about read-only behavior, but for a single-purpose text checker this is close to sufficient.

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?

The schema documents 'text' as 章节正文 while project_id is undocumented, giving 50% coverage. The description's '≤1/章' phrasing reinforces that the unit of analysis is a single chapter, but it adds no meaning for project_id or for how text scope relates to project scope. This is the minimum-viable level for a partially documented two-parameter 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 specific verb and resource (AI 味审计, an 'AI-flavor' audit) and enumerates the exact checks it performs: red-card words, greasy wording, sentence patterns with numeric thresholds, and paragraph-end elevation detection. That makes it distinguishable from format/pacing siblings in practice, but it never names a sibling or states its boundary, so differentiation is inferred rather than stated.

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 【执行层/质检层】 tag hints that this runs in a review/QA stage after drafting, which is implied usage context. There is no explicit statement of when to run it versus check_format, check_pacing, or check_redline, and no preconditions or exclusions are given.

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