Skip to main content
Glama
chacharin

mcp-lightrag

by chacharin

clear_all_documents

Wipes the entire knowledge base by deleting every document permanently. Also can clear LLM cache and parsed files for a complete reset.

Instructions

DESTRUCTIVE: permanently deletes EVERY document in the knowledge base. This cannot be undone -- confirm with the user before calling this.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
clear_llm_cacheNoAlso drop the entire LLM response cache. Off by default so re-adding the same documents can reuse already-paid-for extraction results.
delete_parsed_filesNoAlso delete parsed-artifact files. Off by default so they survive re-adding the same documents later.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that the operation is destructive, permanent, and cannot be undone, and it instructs the agent to confirm with the user. It also implies the default behavior of the two boolean parameters (off by default to preserve cache/parsed files), which adds behavioral context beyond the schema.

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

Conciseness5/5

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

Three sentences with zero waste. The destructive warning is front-loaded, the permanence is stated, and the user-confirmation instruction is included. Every sentence earns its place.

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 destructive bulk operation with an output schema and fully documented parameters, the description covers the critical safety context. It could mention what the response contains or whether the operation is synchronous, but the output schema likely covers return values, and the safety-critical information is complete.

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 the schema already documents both parameters thoroughly. The description adds the context that both are off by default to preserve reusability, which is helpful but not a major addition beyond the schema's own descriptions.

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?

The description states a specific verb ('deletes') and resource ('EVERY document in the knowledge base'), and the DESTRUCTIVE label plus 'permanently' makes the scope unmistakable. It clearly distinguishes itself from sibling delete_documents by targeting all documents rather than a subset.

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 description explicitly says to confirm with the user before calling, which is a clear usage guideline. It doesn't explicitly name alternatives or when-not-to-use, but the destructive nature and confirmation requirement provide adequate context for an agent to know this is a last-resort operation.

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