Skip to main content
Glama
Sign In
Cachly — AI Cognitive Brain

Cachly — AI Cognitive Brain

by cachly-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

compact_recover

Rebuild full context after hitting a context limit or compaction. Recovers session history, work-in-progress data, and open failures from memory, producing a condensed briefing so the AI continues work without losing progress.

Instructions

Call FIRST after any context limit hit / compaction. Reconstructs full context from Memory Crystal + recent sessions + WIP registry + open failures. Returns a condensed briefing so the new context window starts exactly where the previous one left off — no lost progress.

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": {
      "instance_id": "<instance_id>"
    },
    "name": "compact_recover"
  }
}

Input Schema

NameRequiredDescriptionDefault
focusNoWhat you were working on (helps filter relevant context)
instance_idYesBrain instance ID

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.9
    • changedInput schema / properties / focus / description
      Previous value: -"What you are trying to recover context for — used to surface relevant lessons (optional)"New value: +"What you were working on (helps filter relevant context)"
    • changedInput schema / properties / instance_id / description
      Previous value: -"UUID of the cache instance"New value: +"Brain instance ID"
  2. Addedv0.6.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations provided, the description takes full responsibility for behavioral disclosure. It details the sources used (Memory Crystal, recent sessions, WIP registry, open failures) and the outcome (condensed briefing, no lost progress). This gives an agent meaningful transparency about inputs and effects, though potential side effects (e.g., if it mutates state) are not mentioned.

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?

The description is two sentences with zero wasted words. It front-loads the critical usage instruction ('Call FIRST...') and follows with concise explanation of behavior and result. Every sentence serves a clear purpose.

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?

Given the tool has two parameters, no output schema, and no annotations, the description covers the core behavior, usage scenario, and output. It does not explain domain-specific terms (Memory Crystal, WIP registry) or potential side effects, but for an agent in this domain, it likely provides sufficient context to invoke correctly.

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?

The parameter schema has 100% description coverage, with instance_id and focus clearly documented. The tool description reinforces the focus parameter's purpose ('helps filter relevant context'), but adds no new semantic value beyond the schema. Baseline 3 is appropriate as the schema does the heavy lifting.

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 clearly states the tool's purpose: to reconstruct full context after a context limit hit or compaction. It uses a specific verb ('reconstructs') and identifies the resource ('full context'). However, it does not explicitly differentiate from siblings like memory_consolidate or recall_context, which may have overlapping roles, though the 'FIRST' instruction provides implicit distinction.

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?

The description provides explicit usage guidance: 'Call FIRST after any context limit hit / compaction.' This clearly indicates the condition and priority. It does not list alternatives or when not to use, but the strong directive is adequate for an agent to understand when to invoke this tool.

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