bettermemory

Overview Schema Source Related Servers Discussions Admin

memory_verify

Verify a stored memory's claims against the current filesystem and git state, stamping its verification timestamp only when paths, versions, and configurations still match reality.

Instructions

Bump last_verified_at to now after spot-checking that a memory's claims still match reality (file paths exist, version still matches, configuration still what it says).

Orthogonal to content edits: this tool does NOT bump updated; memory_update does NOT bump last_verified_at. A typo fix bumps updated only; a verify call bumps last_verified_at only. Idempotent — calling twice slides the timestamp forward.

Parameters:

id: memory id.
note (optional, ≤800 chars): what was checked, for the event log.
verified_paths (optional list of strings): the ONLY attestation the drift legs read — checked against the memory's own worktree, and the anchor narrowing commit drift. Prefer it when the memory cites paths. Paths absent here are REFUSED. Stored entries re-check when None preserves them — a vanished one blocks the stamp; pass a corrected list.
verified_commits / verified_versions (optional lists): audit trail only; nothing on the read path resolves them.
verified_absent_paths (optional): attest paths INTENTIONALLY absent here (remote host, other platform, not-the-location) — reported under expected_absent, not missing. Never for real drift.
claims (optional): memory_write's claim syntax; checked NOW, false ⇒ refused. Stored claims re-check on every verify — a false one blocks the stamp; memory_update first. All five lists are REPLACE, not append — None preserves the prior attestation, [] clears it, a populated list supersedes it. Attest the full set each time. A verify attesting nothing on a memory whose cited paths resolve is refused; the error lists them as the paths to attest.

The stamp records the origin checkout's HEAD as verified_head; commit drift then counts the commits reachable since it (basis: reachability), which sees a branch merged after the stamp.

After memory_update on a memory you later spot-check, verify again — memory_update clears last_verified_at because the prior verification was for prose that no longer exists.

Returns status="stale" when another agent verified first; the hint says to re-fetch and re-attest.

Also resolves an unresolved record_use(contradicted) flag in memory_health when the body still matches reality.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`note`	No
`claims`	No
`verified_paths`	No
`verified_commits`	No
`verified_versions`	No
`verified_absent_paths`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv3.40.0Aug 5, 2026

addedInput schema / properties / claims

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

First observedv3.34.0Aug 1, 2026

TDQS

A5/5.0

Behavior5/5

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

With no annotations, the description carries the full behavioral burden and fully delivers: idempotency, no mutation of `updated`, replace-not-append list semantics, refusal conditions, `verified_head` tracking, stale status behavior, and resolution of the contradicted flag. It discloses side effects and edge-case behavior in detail.

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?

The description is long, but every section earns its place: parameters, list replacement semantics, stamping behavior, post-memory_update guidance, stale status, and health flag resolution. It is front-loaded with the core purpose and uses clear paragraph breaks for distinct behavioral concerns, with no filler.

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 tool with 7 parameters and subtle behavioral rules, the description is complete: it covers all parameters, refusal cases, preservation vs. clearing semantics, drift detection, stale return status, and interaction with memory_update and memory_health. An agent has enough information to invoke the tool correctly without external knowledge.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must explain all seven parameters. It does so thoroughly: `id`, `note` with character limit, `verified_paths` with the critical attestation semantics, `verified_commits`/`verified_versions` as audit-only, `verified_absent_paths` as intentional absences, and `claims` with false-claim refusal behavior.

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 description opens with a specific verb and resource: it bumps `last_verified_at` after spot-checking claims against reality. It also names the sibling distinction explicitly by stating that memory_update does not bump `last_verified_at` and this tool does not bump `updated`, making the tool immediately distinguishable.

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?

The description gives clear when-to-use guidance: use it after spot-checking, re-verify after memory_update because that operation clears `last_verified_at`, and it contrasts against memory_update for content edits. This is explicit enough for an agent to choose correctly between siblings.

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

Deploy Server