Skip to main content
Glama
Kaede Recall MCP

Kaede Recall MCP

memory-delete

Delete a stored memory by exact ID or semantic match; use dry-run mode to preview matches before removal.

Instructions

Delete a memory by exact id or by semantic match, with a dry-run preview. The only way to remove a node.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory-delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax memories to delete by query, default 1
queryNoSemantic query used to find the memories to delete. Mutually exclusive with 'point_id'.
dry_runNoPreview the matches without deleting anything
point_idNoExact id to delete. Deterministic and preferred. Mutually exclusive with 'query'.
score_thresholdNoMinimum similarity for a match to be deleted

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.10.0

TDQS

A3.7/5.0
Behavior3/5

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 does disclose a dry-run preview, which is valuable safety context for a destructive operation, but it never states that deletion is permanent/irreversible, what happens when multiple matches are found, or permission requirements.

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 short sentences, front-loaded with the action and its modes, with the differentiator placed last. No wasted wording.

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?

For a 5-parameter destructive tool with no annotations and no output schema, the definition covers selection modes and dry-run but omits irreversibility, multi-match/limit behavior, and error conditions when both query and point_id are supplied.

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 limit, query, dry_run, point_id and score_threshold are all already documented, including mutual exclusivity and the preference for point_id. The description merely restates id/query/dry-run at a high level and adds no new semantics.

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 specific verb+resource ("Delete a memory") and enumerates the two selection modes (exact id, semantic match) plus dry-run. The closing line "The only way to remove a node" positively differentiates it from memory-recall/update/write siblings.

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?

Implies the two supported paths and rules out other removal routes, but gives no explicit routing advice such as when to prefer query matching over point_id, or when to set dry_run. Guidance is inferable rather than stated.

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