Skip to main content
Glama

drift_callback

Detect novel-writing drift symptoms and match them to six corrective callback strategies for quality control.

Instructions

【质检层·第三层】漂移回调:输入漂移症状关键词,匹配 6 类回调方案(05 号)。

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": {
      "symptom": "<symptom>"
    },
    "name": "drift_callback"
  }
}

Input Schema

NameRequiredDescriptionDefault
symptomYes症状描述,如:主角开始长篇解释计划 / 反派一碰就倒 / 连续出现抽象情绪
project_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full burden. It doesn't say whether this is a read-only lookup or something that registers/records a callback, whether results are ranked or exhaustive, or what a returned '方案' contains. The phrase '匹配 6 类回调方案' hints at a fixed lookup table but doesn't confirm read-only semantics.

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

Conciseness3/5

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

One short sentence with the layer tag front-loaded, so there is no wasted filler. But the compression goes too far: the layer label, the '6 类' count, and '(05 号)' consume space while conveying little to an agent unfamiliar with the numbering scheme.

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?

A two-parameter tool with no annotations and no output schema relies entirely on the description, which leaves the return value, the six plan categories, and the role of project_id unexplained. An agent could not predict what it will receive or how to act on the result.

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?

Schema coverage is 50%: 'symptom' is documented with examples, but 'project_id' has no description anywhere. The description only echoes 'symptom keywords' and even introduces mild tension with the schema, whose examples are full descriptive sentences rather than keywords. It adds almost no meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

It states a verb (match) and a resource (callback plans keyed by drift symptoms), which is more than a restatement of the name. However, key terms like '漂移' (drift) and '回调方案' (callback scheme) are domain jargon left undefined, and '(05 号)' / '6 类' are cryptic labels that don't help an agent understand what it gets back. The function is roughly inferable but not crisp.

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?

The only positioning cue is the tag '【质检层·第三层】', which implies this belongs to a later stage of a quality-check pipeline. There is no explicit statement of when to call this versus siblings such as check_ai_flavor, check_pacing, or query_method, and no when-not guidance or prerequisites.

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