Skip to main content
Glama
liza-studio

skillmem — long-term memory for Claude Code & Codex

by liza-studio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

mem_update

Update an existing memory's text or metadata while preserving prior versions in SHA256-chained history and requiring a reason; owner approval drops when approved words change.

Instructions

Change the text or metadata of an existing memory. WRITES: replaces title/body/fields, keeps the previous version in the SHA256-chained history under the required reason, marks the text origin='agent' and DROPS the owner's approval — approval belongs to the words that were approved. Same text with new metadata changes only the metadata and keeps approval. Fields omitted stay as they were, a field sent as null is cleared; ttl_days cannot be changed here. Fails for an unknown or deleted slug (create with mem_write), an archived one, and a record the owner wrote or approved (only the owner changes it; write a proposal under a new slug). Returns ok, slug and the history length. Use mem_reinforce to report how a skill worked instead of editing it; retiring a record retire a record without editing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYes
kindNo
slugYes
tagsNo
titleNo
reasonYesWhy this update was made.
topicsNo
projectNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.12.0
    • changedInput schema / properties / project / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedInput schema / properties / tags / type
      Previous value: -"array"New value: +[
+  "array",
+  "null"
+]
    • changedInput schema / properties / title / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedInput schema / properties / topics / type
      Previous value: -"array"New value: +[
+  "array",
+  "null"
+]
  2. Changed1 schema field changedv0.11.0
    • removedInput schema / properties / agent
      Removed value: -{
-  "type": "string"
-}
  3. First observedv0.10.5

TDQS

A4.8/5.0
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 does so richly: it discloses the SHA256-chained history kept under the required reason, the approval being dropped for text changes, origin='agent' marking, null-means-clear vs omitted-means-unchanged semantics, that ttl_days is immutable here, failure conditions (unknown/deleted/archived/owner-written), and the return shape (ok, slug, history length).

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?

Very dense and largely front-loaded, with writes/history/approval behavior stated first and edge cases after; nearly every clause adds actionable meaning. The final clause is garbled ('retiring a record retire a record without editing'), costing a point.

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 an 8-parameter mutation tool with no output schema and no annotations, the description nevertheless covers mutation semantics, versioning, permission model, failure modes, and return values. Nothing an agent needs in order 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 only 13%, so the description must compensate, and it does for the semantically tricky parts: required reason, required body, omitted-vs-null field behavior, and the ttl_days exclusion. It leaves kind, tags, topics, and project entirely unexplained, which is a real gap given the low coverage.

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 (change) and resource (text/metadata of an existing memory) and immediately differentiates from siblings by naming mem_write, mem_reinforce, and retirement. An agent can tell what this does versus the other mem_* tools 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?

Explicitly routes usage: create unknown/deleted slugs with mem_write, write proposals for owner-authored records, use mem_reinforce to report skill outcomes, and retire rather than edit. When-not-to-use is spelled out alongside alternatives.

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

Deploy Server

Other Tools