Skip to main content
Glama

check_redline

Detects publishing redlines in chapter text—commands/paths, annotation leaks, Markdown residue, real company names, title exclamation marks—and blocks release on fatal findings without LLM calls.

Instructions

【L1】形态红线毫秒级检查:可复现命令/路径、内部标注泄漏、Markdown 残留、真实企业名、章名感叹号。致命项直接判禁止发布(不调任何 LLM)。

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_redline"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
platformNo
chapter_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden, and it discloses important traits: the check is deterministic and fast ("毫秒级") because it makes no LLM calls, and fatal findings hard-block publication. That blocking consequence is the key behavioral fact an agent needs. It does not describe what the response looks like or how non-fatal findings are reported.

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 description is one dense sentence, front-loaded with the level tag and the check category before the enumerated items, and it includes the critical blocking consequence. Nothing is padded, although the run-on enumeration is slightly harder to scan than a structured list would be.

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?

Considering the complexity of a three-parameter checker with no output schema and no annotations, the description covers what is checked and the publish-blocking behavior well. It is still incomplete because it leaves all three parameters undefined and the shape of the result unspecified, which an agent needs to build a correct call.

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 description coverage is 0% across three parameters (text, platform, chapter_id), so the description must compensate, but it does not. It does not explain what text should contain, what platform controls, or how chapter_id affects the check; the mention of "章名" hints at chapter titles but does not tie that to the chapter_id parameter. Only the enumerated check list gives any indirect context.

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 action (a red-line inspection) and enumerates exactly what it checks: reproducible commands/paths, internal annotation leakage, Markdown residue, real company names, and exclamation marks in chapter titles. It also scopes the tool as a level-1, millisecond-level check, so the agent can tell it apart from the other checks that its sibling tools perform. It stops short of naming an alternative sibling and explaining the difference, which a 5 would require.

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 only implied: the description says a fatal item leads to being judged as prohibited from publishing, which suggests a pre-publication gate, and the "不调任何 LLM" note signals that this is a fast first pass. There is no explicit statement of when to use this tool instead of check_format or check_ai_flavor, and no prerequisites or ordering guidance.

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