Skip to main content
Glama

mcp_engram_forget_old

Evict stale, unpinned memories by CRS threshold or age to trim growing memory manifold. Pinned memories are protected. Use after project phases to consolidate.

Instructions

Manually trigger autophagy: evict all non-pinned memories below a CRS threshold. WHEN TO USE: After a long project phase ends, after distill runs, or when the manifold is growing too large. Start conservative (min_crs_threshold=0.3) and increase if needed. Pinned blocks (CRS=1.0) are ALWAYS exempt and will never be evicted. Use older_than_days to target stale memories while preserving recently-accessed ones. Preview what would be evicted with mcp_engram_stats first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
min_crs_thresholdNoEvict memories with CRS below this value (default: 0.2)
older_than_daysNoIf set, only evict memories not accessed in this many days
Behavior4/5

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

Discloses that pinned blocks (CRS=1.0) are always exempt, which is a critical behavioral detail. Lacks mention of irreversibility or error conditions, but for an eviction tool the description is fairly transparent.

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?

Concise 4-sentence structure with clear sections, no redundancy. Every sentence adds value, and the 'WHEN TO USE' format improves scanability.

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?

Missing output schema and does not mention what the tool returns (e.g., count of evicted memories). While the description is strong on usage, omitting return value information reduces completeness for an agent.

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 covers both parameters with descriptions, but the tool description adds strategic context (e.g., 'target stale memories while preserving recently-accessed ones') and practical guidance on threshold values, going beyond the schema.

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?

Description clearly states 'evict all non-pinned memories below a CRS threshold' and mentions optional age filtering, making the tool's purpose explicit and distinct from siblings like 'forget' and 'mcp_engram_stats'.

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?

Includes a dedicated 'WHEN TO USE' section with three concrete scenarios, plus advice to start conservative and preview with mcp_engram_stats. Provides clear context for decision-making.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/staticroostermedia-arch/engram'

If you have feedback or need assistance with the MCP directory API, please join our Discord server