Skip to main content
Glama
ClickHouse Loom

ClickHouse Loom

Official

loom_memory_get

Read-onlyIdempotent

Fetches a single stored memory by exact key when a user names the key explicitly, returning whether it was found and its value; use search for natural-language recall.

Instructions

WHAT: Fetch one memory by exact memory_key. WHEN: The user names a key explicitly ('what is foo_bar in Loom?', 'show me the value of user_employer'). The response shape includes found: true/false + value. WHEN NOT: Don't call for natural-language recall — that's loom_search. On found: false, fall through to loom_search; the key might have a slightly different name. ARGS: Just the memory_key. Server fills the identity tuple. fields: [value, tags, status, …] returns only those output fields (plus found) when the whole row is not needed. follow: true serves the live canonical of a duplicate row (resolved_from = the key asked for, canonical_key = the key served).

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_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNo
fieldsNo
followNo
run_idNo
namespaceNo
if_versionNo
memory_keyYes
include_recall_breakdownNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description goes beyond by disclosing the `found: true/false` + `value` response contract and the duplicate-resolution behavior of `follow` (`resolved_from` vs `canonical_key`). It does not discuss identity-tuple resolution beyond 'server fills it' or any namespace/auth constraints, which keeps it short of a 5.

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?

Labeled WHAT/WHEN/WHEN NOT/ARGS sections front-load the decision-relevant content ahead of argument detail, and every sentence carries either routing or behavioral information. No filler or restatement of the tool name.

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?

There is no output schema, and the description does compensate by naming the response shape and the follow-resolution fields. However, for an eight-parameter tool with zero schema coverage, five undocumented parameters leave an agent guessing about temporal reads, version pinning, and namespace scoping.

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 0%, so the description must carry parameter meaning and it only covers three of eight: `memory_key` (exact match), `fields` (field projection plus `found`), and `follow` (canonical serving). `as_of`, `run_id`, `namespace`, `if_version`, and `include_recall_breakdown` are left entirely undefined in both schema and description, which is a meaningful gap for a point-read tool where version and temporal scoping change results.

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 WHAT line states a specific verb and resource ('Fetch one memory by exact `memory_key`') and immediately scopes it against the alternative (natural-language recall belongs to loom_search). An agent can distinguish this from loom_search, loom_memory_list, and loom_knowledge_get without opening any schema.

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?

Explicit WHEN with concrete trigger phrasing ('what is foo_bar in Loom?'), explicit WHEN NOT pointing at loom_search, and a recovery path on `found: false`. This is the full when/when-not/alternative triad with no inference required.

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