Muninn (munn.is)

muninn_reconcile

DestructiveIdempotent

Scan all memories for orphan/inconsistency issues across KV, D1 tag index, and Vectorize. Pass repair:true to fix gaps. Returns a report of what was found and (if repair) what was fixed. For large accounts, pass limit + cursor to process one batch per call (a Worker invocation caps at 1000 subrequests) — the report's nextCursor feeds the next call until it's null. With reindexAll:true every memory's vector is re-embedded unconditionally (used for the vector-id format migration) instead of only re-embedding vectors detected as missing.

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": "muninn_reconcile"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max memories to process this call. Omit to process ALL (may exceed the Worker subrequest cap on large accounts). Use ~150 for batched migration.
`cursor`	No	KV pagination cursor from a previous call's nextCursor. Omit for the first batch.
`repair`	No	If true, repair gaps: re-index missing D1 tags and re-embed missing Vectorize vectors. If false, report only.
`reindexAll`	No	If true (with repair), re-embed + re-upsert EVERY memory's vector unconditionally — skips the existence probe (saves one AI call + one query per memory). Use for the vector-id format migration.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds real behavioral context beyond the annotations: the Worker subrequest cap, one-batch-per-call semantics with nextCursor chaining, and exactly what repair vs reindexAll mutate. It does not explicitly warn about the destructiveHint=true annotation (what gets overwritten), which is a minor gap given the annotation already flags it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then pagination mechanics, then the reindexAll special case. Every sentence carries information, though the final reindexAll sentence is dense and could be tighter.

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 complex, no-required-param maintenance tool with no output schema, the description covers invocation modes, batching workflow, migration path, and summarizes the return (a report of found/fixed items plus nextCursor). Nothing an agent needs to call it correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: cursor is tied to the previous call's nextCursor, limit is the batch control, and reindexAll's migration purpose plus its 'skips the existence probe' behavior. This goes beyond the schema descriptions rather than restating them.

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 (Scan) plus resource and scope: 'all memories for orphan/inconsistency issues across KV, D1 tag index, and Vectorize.' This is precise enough to separate it from sibling tools like muninn_mirror_reconcile, which operates on a different resource.

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

Usage Guidelines4/5

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

Gives clear when-to-use guidance for each mode: repair:true to fix vs report-only, limit+cursor for large accounts due to the 1000-subrequest cap, and reindexAll:true specifically for the vector-id format migration. It does not name a sibling alternative or state when not to run it, so it stops short of a 5.

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

All Muninn (munn.is) tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?