Skip to main content
Glama

memory_archive

Destructive

Archive a memory by ID to remove it from default retrieval and briefings while preserving searchable history. Use when content is stale or superseded, not for deleting valuable memories.

Instructions

归档一条记忆(HTTP 模式必须传 project);用户级记忆可从任意项目视图按 id 归档。退出默认检索与项目简报,但保留可查历史。内容失效或被取代时使用;不要删除仍有价值的记忆。

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": {
      "id": "<id>"
    },
    "name": "memory_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
projectNo项目名或 id。省略时从当前工作目录自动解析
expected_versionNo乐观并发:传你读到的 memory.version,被并发修改时报 REVISION_CONFLICT

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.4

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, and the description adds the crucial nuance that the operation is a soft removal — the record leaves default retrieval and the project brief but history stays queryable. It also discloses the HTTP-mode project requirement, which the annotations cannot express. Return shape and idempotency are not covered, keeping 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.

Conciseness4/5

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

Compact and front-loaded: purpose first, then scope nuance, then effect, then when-to-use, then the caution. The semicolon-chained second sentence packs several distinct facts together, which slightly reduces scannability but wastes no words.

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

Completeness4/5

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

For a three-parameter mutation with no output schema, the description covers effect (soft archive), preconditions (HTTP requires project), and the use/don't-use boundary. Remaining gaps are secondary: no statement of what the response contains or whether re-archiving the same id is a no-op.

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?

With 67% schema coverage, the schema already documents project (auto-resolved from cwd) and expected_version (REVISION_CONFLICT). The description adds genuine context that project becomes mandatory in HTTP mode and that user-level memories can be archived by id from any project view, which clarifies the id/project interaction beyond the schema. expected_version is not discussed in the description at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (归档一条记忆) and states the effect precisely: the memory exits default retrieval and the project brief but remains queryable in history. That distinguishes it from an outright delete, though no sibling tool (e.g. memory_update/memory_write) is named as the contrasting alternative.

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?

It gives an explicit trigger ('内容失效或被取代时使用') and an explicit exclusion ('不要删除仍有价值的记忆'), plus an operational precondition that HTTP mode requires project. What is missing is a named alternative — it never says to prefer memory_update when the content is merely stale rather than superseded.

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