Cachly — AI Cognitive Brain

cache_keys

Retrieve cache instance keys matching a glob pattern using SCAN to prevent server blocking. Optionally limit results and set pattern.

Instructions

List keys in a cache instance matching an optional glob pattern (e.g. "user:", "session:"). Uses SCAN to avoid blocking the server. Returns at most count keys.

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": "cache_keys"
  }
}

Input Schema

Name	Required	Description
`count`	No	Max keys to return (default: 50, max: 500)
`pattern`	No	Glob pattern (default: *)
`instance_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Apr 21, 2026

TDQS

A4.1/5.0

Behavior4/5

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

The description discloses that it uses SCAN (non-blocking), supports optional pattern, and returns at most count keys. Without annotations, it provides good behavioral context, though it omits details on potential duplicates or response format.

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?

Two sentences efficiently convey the purpose, behavior, and constraints. The first sentence front-loads the core action, and every word adds necessary information.

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?

Given the absence of an output schema, the description should hint at what is returned (e.g., an array of key strings). It covers input and behavior well but lacks return format, leaving a gap for a complete understanding.

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?

The description adds value beyond the schema by providing example glob patterns for 'pattern' and explaining the 'count' parameter with defaults and max. However, 'instance_id' lacks description in both schema and description.

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?

The description clearly specifies the verb 'List' and the resource 'keys in a cache instance', and provides example glob patterns. This distinguishes it from sibling tools like cache_get or cache_set, which deal with individual key values.

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?

While the description mentions using SCAN to avoid blocking, it does not explicitly state when to use this tool vs alternatives (e.g., cache_mget for specific keys). Usage context is implied but not contrasted with siblings.

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

Deploy Server