raggy-mcp

raggy_forget

Remove or redact stored memories from the knowledge graph when users ask to forget or delete a memory. Supports full deletion or content stripping while preserving links.

Instructions

Call immediately when the user says "forget that", "don't save that", or "delete that memory". Use mode="delete" to remove entirely or mode="redact" to preserve the graph node but strip content. Not for uploaded sources — use raggy_delete_source for those.

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": {
      "memory_id": "<memory_id>"
    },
    "name": "raggy_forget"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No	"delete" (default) removes completely, "redact" preserves metadata/links
`memory_id`	Yes	The memory ID to forget

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Sep 6, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden for destructive behavior. It explains that delete removes entirely and redact preserves the graph node while stripping content, which goes beyond the schema wording. It does not mention reversibility or permission requirements, but the main side-effect profile is clear.

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?

Two sentences front-load the trigger conditions and mode choices, then add the sibling exclusion. Every sentence contributes value and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema, the description fully supports correct selection and invocation: when to call, which mode to pick, and which sibling to use for uploaded sources.

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 memory_id and mode. The description re-explains mode semantics ('delete removes entirely' vs 'redact preserves graph node') but adds no new parameter-level syntax or constraints.

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 names the exact trigger phrases ('forget that', 'don't save that', 'delete that memory') and the resource (memories), so the tool's purpose is unambiguous. It also disambiguates from raggy_delete_source by saying uploaded sources are out of scope.

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

Usage Guidelines5/5

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

It opens with explicit invocation instructions ('Call immediately when...') and then gives the mode choice. It closes with a clear exclusion: uploaded sources should go to raggy_delete_source instead.

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

Deploy Server