lore-mcp

kb_backfill_embeddings

Backfill embeddings for KB entries that are missing or stale due to model or content changes. Idempotent operation skips entries with matching content hashes.

Instructions

Embed any KB entries that are missing or stale (model/content changed). Idempotent: skips entries whose stored content_hash still matches. Requires LORE_SEMANTIC_SEARCH=true.

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": "kb_backfill_embeddings"
  }
}

Input Schema

Name	Required	Description	Default
`batch_size`	No
`limit`	No
`dry_run`	No
`confirm_production`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.8.5May 28, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / batch_size / description

Removed value: -"How many entries to encode per batch (default 32)."

removedInput schema / properties / batch_size / maximum
```
Removed value: -512
```
removedInput schema / properties / batch_size / minimum
```
Removed value: -1
```

removedInput schema / properties / confirm_production / description

Removed value: -"Required (true) to run a real backfill when LORE_ENV=production. Guards against accidental large-scale writes; ignored for dry runs and non-prod."

removedInput schema / properties / dry_run / description

Removed value: -"If true, report what would be embedded without writing."

addedInput schema / properties / limit / anyOf

Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / limit / default
```
Added value: +null
```

removedInput schema / properties / limit / description

Removed value: -"Optional cap on entries to process this run."

removedInput schema / properties / limit / minimum
```
Removed value: -1
```
removedInput schema / properties / limit / type
```
Removed value: -"integer"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "type": "object",
+  "x-fastmcp-wrap-result": true
+}

First observedv0.7.0May 25, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Discloses idempotency and skipping behavior based on content hash. No annotations provided, so description carries the burden; it adds meaningful behavioral context beyond 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?

Two efficient sentences with no wasted words. Front-loaded with action and condition.

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

Completeness2/5

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

Lacks parameter documentation and output schema description. With 4 parameters and no coverage, the description is incomplete for proper invocation.

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

Parameters1/5

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

Schema description coverage is 0%, and the description does not mention any of the 4 parameters (batch_size, limit, dry_run, confirm_production), failing to compensate for the gap.

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?

Clearly states the verb 'embed' and resource 'KB entries that are missing or stale', with specific condition (model/content changed). Distinguishes from siblings like kb_embedding_status or kb_add.

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 usage for refreshing stale embeddings but does not explicitly state when to use versus alternatives (e.g., kb_ingest_* or kb_update). Only mentions a prerequisite environment variable.

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