Skip to main content
Glama
furui

furui

Prune

prune

List or delete unpinned memories whose score falls below a threshold; dry-run lists candidates by default, and disabling it deletes them.

Instructions

List or delete unpinned memories whose current score is below a threshold.

A brand-new importance-1 memory scores 1.0; an importance-3 memory left untouched for one half-life scores 1.5. Thresholds around 0.25-1.0 are typical.

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": {
      "threshold": "<threshold>"
    },
    "name": "prune"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNoIf true (default) only list candidates; if false, delete them.
thresholdYesMemories with score strictly below this are candidates.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose a meaningful safety scoping rule — only unpinned memories are candidates, so pinned memories are never touched — and it explains that listing versus deleting is a mode choice. It stops short of stating whether deletion is permanent/irreversible or what permissions are required.

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?

Three short sentences: the operation first, then the scoring model, then a practical range. Nothing is redundant and the most decision-relevant information is front-loaded.

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?

An output schema exists, so return values need not be described, and the two parameters are fully documented in the schema. The description covers the important scoping and scoring context but leaves irreversibility of deletions and side effects on any related data unstated for a tool that can perform destructive writes.

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 100%, so the baseline would be 3, but the description adds real meaning beyond the schema by explaining what the threshold number actually represents (a new importance-1 memory scores 1.0; an importance-3 memory after one half-life scores 1.5), grounding the abstract number in observable outcomes.

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 pair and resource: list or delete unpinned memories below a score threshold. The 'unpinned' qualifier and the scoring explanation make the operation concrete. It does not explicitly contrast itself with the sibling 'forget', so sibling differentiation is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied ('prune low-scoring memories') and reinforced by concrete threshold guidance ('Thresholds around 0.25-1.0 are typical'), which helps an agent choose a parameter value. However, there is no explicit statement of when to prefer this over 'forget' for deliberate deletion, and no stated exclusions.

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