Skip to main content
Glama

check_self_consistency

Detect timeline regressions, conflicting numbers, and inconsistent titles within a single chapter; returns suspect flags with source evidence for human or L3 review.

Instructions

【弱信号·零成本】单章内部自洽:时序倒退 / 数字互斥 / 称谓变体。只报 suspect + 原文证据,绝不判 fatal/reject,最终需 L3 或人工复核。

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_self_consistency"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does so well: it discloses severity policy (never fatal/reject), output semantics (suspect flag plus verbatim source evidence), and a mandatory downstream review step. Remaining gaps are input-size expectations (single chapter only) and the meaning of the internal 'L3' tier.

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?

Extremely dense and front-loaded: the cost/severity qualifier comes first, then the detection scope, then the output policy. Minor deduction because the unexplained 'L3' token and bracket notation assume project-internal jargon the agent may not share.

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?

For a one-parameter, annotation-free, no-output-schema tool, the description covers scope, detection targets, severity ceiling, evidence format, and escalation. It is nearly sufficient; only the meaning of 'L3' and the unit-of-input constraint are left implicit.

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 single 'text' parameter has 0% schema description coverage, but the description partially compensates by implying it is exactly one chapter's text ('单章内部自洽'). It adds no detail on format, length limits, or whether multi-chapter input is rejected.

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

Purpose5/5

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

States a concrete verb and scope (intra-chapter self-consistency) and enumerates the three detection categories: temporal regression, mutually exclusive numbers, and appellation variants. It also distinguishes itself from stricter checks by declaring it never issues fatal/reject verdicts, so an agent can tell it apart from review/redline siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'weak signal, zero cost' tag plus 'only reports suspect, requires L3 or manual review' clearly frames this as a cheap first-pass scan whose output feeds escalation. It does not explicitly name an alternative tool or state when to skip it, so it stops short of full when/when-not guidance.

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