Skip to main content
Glama
Sign In

aidelly

by io.github.wilzer
OverviewDiscussionsAdmin

Generate Social Analytics Insights

aidelly_generate_analytics_insights

Generate and save AI analytics insights for workspace_id, optionally limited to platforms. regenerate=true forces a fresh analysis even when insights already exist. Default is free rule-based insights; opt in with coach: true for AI patterns across the period (optional date_from, date_to up to 90 days, platform); coach costs 12 credits, and with too little data it falls back to rule-based with a coachUnavailable reason and no charge. aidelly_get_analytics_insights reads saved insights without generating new ones. Retry-safe: a repeat call with the same idempotency_key returns the original result and is not charged again. Coach runs are limited to 5 a minute per API key.

Input Schema

NameRequiredDescriptionDefault
bodyNoOptional body override for endpoints with sparse parameter schemas.
coachNoOpt in to the AI period coach: patterns across the period's posts (what to repeat, change, and test next). Costs 12 AI credits per run, charged to the API key's user. Default false keeps the free rule-based insights. Needs enough published posts; with too little data, or while the coach is not enabled, the response is the rule-based insights plus `coachUnavailable` and nothing is charged.
queryNoOptional query overrides for endpoints with sparse parameter schemas.
date_toNoCoach only. Last day (YYYY-MM-DD, not in the future). Defaults to today (UTC).
brand_idNo
platformNoCoach only. Limit the coach to one platform (e.g. instagram, x). When omitted and `platforms` has exactly one entry, that entry is used; otherwise the coach runs across all platforms.
date_fromNoCoach only. First day (YYYY-MM-DD). Defaults to 30 days before date_to; the range is at most 90 days.
platformsNoPlatforms to analyze for insights.
regenerateNoIf true, force regeneration even if insights exist.
workspace_idNoWorkspace to operate in: the `id` of a workspace returned by aidelly_list_workspaces. Optional for read operations; required when creating content.
idempotency_keyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / coach
      Added value: +{
+  "default": false,
+  "description": "Opt in to the AI period coach: patterns across the period's posts (what to repeat, change, and test next).\nCosts 12 AI credits per run, charged to the API key's user. Default false keeps the free rule-based insights.\nNeeds enough published posts; with too little data, or while the coach is not enabled, the response is the\nrule-based insights plus `coachUnavailable` and nothing is charged.\n",
+  "type": "boolean"
+}
    • addedInput schema / properties / date_from
      Added value: +{
+  "description": "Coach only. First day (YYYY-MM-DD). Defaults to 30 days before date_to; the range is at most 90 days.",
+  "format": "date",
+  "type": "string"
+}
    • addedInput schema / properties / date_to
      Added value: +{
+  "description": "Coach only. Last day (YYYY-MM-DD, not in the future). Defaults to today (UTC).",
+  "format": "date",
+  "type": "string"
+}
    • addedInput schema / properties / platform
      Added value: +{
+  "description": "Coach only. Limit the coach to one platform (e.g. instagram, x). When omitted and `platforms` has exactly one entry, that entry is used; otherwise the coach runs across all platforms.",
+  "type": "string"
+}
  2. Changed4 schema fields changed
    • addedInput schema / properties / idempotency_key / example
      Added value: +"order-123:create-post:v1"
    • addedInput schema / properties / idempotency_key / maxLength
      Added value: +255
    • addedInput schema / properties / idempotency_key / minLength
      Added value: +1
    • addedInput schema / properties / idempotency_key / pattern
      Added value: +"^[\\x21-\\x7E]{1,255}$"
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations: credit cost (12 per coach run), rate limit (5 coach runs/min per API key), fallback behavior (too little data -> rule-based plus coachUnavailable, no charge), and retry safety via idempotency_key. These are the operational facts an agent needs before spending credits that annotations alone don't convey.

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

Conciseness4/5

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

Front-loads the core purpose and consequence-bearing constraints (cost, rate limit, retry) in a tight paragraph. It is dense and slightly crammed into one block, but every sentence carries distinct information.

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?

For an 11-parameter mutation tool with no output schema, the description covers the highest-risk aspects (charges, rate limits, fallback, idempotency) thoroughly. It omits any mention of brand_id and the sparse-schema body/query overrides, leaving a couple of parameters unexplained.

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 high (82%), so baseline is 3, but the description adds real meaning: coach's cost and fallback, regenerate semantics, the 90-day date range cap, and the platform fallback when platforms has exactly one entry. It does not explain brand_id or the body/query override objects, so it stops short of 5.

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?

States a specific compound verb ('generate and save AI analytics insights') plus the resource and its scope ('for workspace_id, optionally limited to platforms'), and explicitly contrasts with the read-only sibling aidelly_get_analytics_insights. An agent can tell it apart from get_analytics_insights and update_analytics_insight without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit selection conditions: default free rule-based, opt into coach for AI patterns, regenerate=true to force a fresh run even when insights exist, and use aidelly_get_analytics_insights to read without generating. When-to-use and the alternative are both named.

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

All aidelly 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