ClickHouse Loom

Official

Overview Schema Source Related Servers Discussions Admin

loom_memory_delete

DestructiveIdempotent

Tombstone an agent memory by key for 14-day dashboard recovery; use only on explicit delete or forget requests. A result with tombstoned false is not success.

Instructions

WHAT: Tombstone a memory by key (14-day recovery in the dashboard). The row is found across every agent and session in the namespace; found: false = no live row — tombstoned: false is never success. WHEN: Explicit user request — 'forget that I…', 'delete X in Loom'. WHEN NOT: Not as cleanup or on inferred intent; to fix a wrong memory, memory.update it with the corrected value. ARGS: memory_key. Server fills identity.

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_key": "<memory_key>"
    },
    "name": "loom_memory_delete"
  }
}

Input Schema

Name	Required	Description	Default
`run_id`	No
`namespace`	No
`memory_key`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.1.0Nov 12, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare destructive=true and idempotent=true, yet the description still adds material behavior: the 14-day recovery window, the tombstone-not-hard-delete semantics, and the crucial result-interpretation rule that 'found: false' means no live row and 'tombstoned: false' is never success. That result-handling guidance is exactly the kind of context annotations cannot convey.

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?

Four labeled sections (WHAT / WHEN / WHEN NOT / ARGS) front-load the action and the guardrail, with no filler sentences. Each line carries distinct information an agent needs for selection or invocation.

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 destructive, 3-parameter tool with no output schema, the description supplies the safety profile, the alternative for the common mistake case, and the meaning of the returned flags. Nothing needed to call it correctly or interpret the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage across 3 parameters, the description must compensate. It names memory_key as the operative argument and states 'Server fills identity', which explains why run_id and namespace are present-but-optional, and it clarifies namespace scoping in the opening sentence. It stops short of describing memory_key format or key conventions, so it is strong but not exhaustive.

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?

Opens with a specific verb and resource — 'Tombstone a memory by key' — and immediately clarifies the mechanism (14-day recovery in the dashboard) plus the lookup scope across every agent and session in the namespace. That distinguishes it cleanly from siblings like loom_memory_update or loom_memory_get without needing their schemas.

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?

Has an explicit WHEN clause quoting the user phrasings that trigger it, and a WHEN NOT clause that both excludes inferred/cleanup uses and names the correct alternative ('memory.update it with the corrected value'). The selection rule is fully determined.

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

Deploy Server