Skip to main content
Glama
Sign In

Humryk

by com.humryk
OverviewDiscussionsAdmin

Newsletter campaign performance

email_campaign_performance
Read-onlyIdempotent

Newsletter campaigns sent in the period, ranked by revenue per recipient: subject, send time, channel, audience note, recipients, clicks, attributed orders, revenue, whether it was discount-led and the verdict; for a two-subject test subjectB and abWinner; plus one insight comparing discount-led and content campaigns. campaign_id gives one campaign (the period is then ignored). For «which subject lines worked best?». how_to_read in the result gives the counting rules.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "email_campaign_performance"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoPeriod end, exclusive (default: now) as an ISO-8601 date or datetime, e.g. 2026-09-01.
fromNoPeriod start (default: 30 days ago) as an ISO-8601 date or datetime, e.g. 2026-09-01.
channelNob2b = orders from business customers, b2c = orders from consumers. Default all.
campaign_idNoOne campaign; omit for every campaign sent in the period.
merchant_idNoShop id; optional with one shop (list_shops).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / merchant_id / description
      Previous value: -"Shop id. Optional when the account has exactly one shop; see list_shops."New value: +"Shop id; optional with one shop (list_shops)."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnly=true, idempotent=true, destructive=false, so safety is covered. The description adds real behavioral context beyond that: results are ranked by revenue per recipient, exactly one comparative insight is included, campaign_id overrides the date range, and counting rules are exposed via how_to_read in the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded, which is good, but the middle is a long semicolon-chained enumeration of output fields that reads as a run-on. The field list earns some of its place because there is no output schema, yet the phrasing could be tightened considerably.

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?

With no output schema, the description correctly takes on the job of describing the return shape and points to how_to_read for counting rules, which suits a read-only reporting tool. It stops short of covering result limits or pagination, so it is strong but not exhaustive.

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?

Schema description coverage is 100%, so the schema already explains every parameter, and the baseline is 3 for that reason. The description contributes only one genuinely new semantic not spelled out in the schema, namely that the period is ignored when campaign_id is supplied.

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 states a specific verb and resource: newsletter campaigns sent in the period, ranked by revenue per recipient, and it enumerates what comes back (subject, send time, channel, clicks, attributed orders, revenue, discount-led flag, verdict, plus subjectB/abWinner for A/B tests). That is far more specific than the name alone. It never names a sibling such as email_flow_performance or email_overview, so the agent must infer the boundary itself.

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?

It gives a concrete triggering question, "which subject lines worked best?", and states that supplying campaign_id switches to single-campaign mode and the period is then ignored. What is missing is any negative guidance: there is no statement about when to prefer email_flow_performance, email_overview or email_whats_working instead.

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

All Humryk toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources