Skip to main content
Glama

memory_review

Read-only

Lists memories whose review date has passed and marks entries as reviewed, restarting their review cycle so project memory stays trustworthy.

Instructions

复审周期(HTTP 模式必须传 project):列出 review_after 已到期的记忆(内容可能过时,仍可检索但带 needsReview 标记),或把某条标记为已复审(周期按 kind 重新起算)。定期处理可保持记忆可信。

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": {
      "action": "<action>"
    },
    "name": "memory_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNomark_reviewed 时的记忆 id
actionYeslist=列出到期记忆;mark_reviewed=标记已复审
projectNo项目名或 id。省略时从当前工作目录自动解析

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.4

TDQS

B3.2/5.0
Behavior1/5

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

The description discloses a state-mutating mode: mark_reviewed sets a memory as reviewed and restarts its cycle by kind, i.e. it writes persistent state. The annotations declare readOnlyHint=true, which directly conflicts with that disclosed mutation. An agent trusting the annotation could call the mutating branch without the caution a write operation warrants.

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?

The description is compact and front-loaded, leading with the mode constraint before the two branches. Each parenthetical adds value (staleness, needsReview flag, cycle restart by kind) rather than restating the name. Slightly dense Chinese prose, but no sentence is wasted.

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

Completeness3/5

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

With no output schema, the description usefully explains the observable result of listing (items flagged needsReview and still retrievable), which is the key return-value context. However, it never states that id is needed for mark_reviewed even though the schema marks only action as required, leaving an agent unsure what happens when id is omitted. Pagination or ordering of the expired list is also unaddressed.

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?

Schema coverage is 100%, so the schema already explains action, id, and project. The description adds one genuinely new constraint not present in the schema: project is mandatory in HTTP mode, while the schema only mentions cwd-based auto-resolution. Beyond that cross-mode note it adds little parameter-level meaning, so the high-coverage baseline of 3 applies.

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 two concrete operations with their resources: listing memories whose review_after has expired, and marking a memory as reviewed. It also clarifies the consequence of each (stale items remain searchable but carry a needsReview flag; marking restarts the cycle by kind). It does not explicitly contrast itself with siblings such as memory_update, but the enum-driven dual mode makes the tool unmistakable.

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 a clear use context — periodic handling keeps memory trustworthy — and a real prerequisite: in HTTP mode project must be passed. That prerequisite is exactly the kind of operational guidance an agent needs before invoking. It stops short of explicit exclusions (e.g., when to prefer memory_update or memory_read), so it is strong but not complete.

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