@lodd/mcp-server

get_actor_retention

Analyze weekly cohort retention by actor hash. Groups actors by first appearance week and tracks return rates across weeks 1-4.

Instructions

Get weekly cohort retention by actor hash. Groups actors by the week they first appeared, then shows how many returned in weeks 1-4. Actors are opaque hashes — no personal data is stored or exposed. Requires 2+ weeks of data for meaningful results.

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": {
      "site": "<site>"
    },
    "name": "get_actor_retention"
  }
}

Input Schema

Name	Required	Description	Default
`site`	Yes	Site domain or UUID
`period`	No	Time period (use 90d for meaningful cohorts)	90d

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.15Jul 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations provided, the description carries full responsibility. It clarifies that actors are opaque hashes and no personal data is stored or exposed, adding important privacy context beyond the basic function. It stops short of stating safety properties like idempotency, but still provides meaningful behavioral insight.

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 only two sentences, both concise and informative. It avoids unnecessary detail while covering purpose, mechanics, and a usage hint. Every sentence earns its place.

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's simplicity (2 parameters, no output schema), the description is largely complete. It explains the cohort logic and data requirement. A minor gap is the lack of description of the output format, but overall it provides sufficient context for an agent to use the tool correctly.

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 schema already describes both parameters (site and period) with 100% coverage. The description adds value by recommending using '90d' for meaningful cohorts, which goes beyond the default value. This extra guidance helps the agent choose appropriate input.

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 states the tool retrieves weekly cohort retention by actor hash, and explains the grouping logic. This is a specific verb-resource combination that distinguishes it from sibling analytics tools which focus on other metrics.

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?

The description mentions a prerequisite (2+ weeks of data for meaningful results), providing some guidance on when to use. However, it does not explicitly state when not to use or suggest alternative tools, which limits its helpfulness for decision-making.

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