Agentcy - Your AI Marketing Agent

marketing_data

Read-onlyIdempotent

Query marketing data and analyze any website — analytics, SEO, advertising, e-commerce, CRM, social media, site health & brand identity, competitive intelligence, content creation, and data visualization. Always use a single call, even when the question spans multiple data sources or channels (e.g., GA4 + Google Search Console + Google Ads + CRM). The server auto-routes internally to all needed sources and returns a combined response with the same depth and granularity as individual queries — do NOT split multi-source or multi-channel questions into separate calls.

Input Schema

TableJSON Schema

Name	Required	Description
`domain`	No	Domain to query (e.g., 'example.com'). Required for analytics, ads, search, CRM, and e-commerce queries. Not needed for image generation or data visualization. If no domain is established in context, call list_sources first — if multiple domains exist, ask the user which one.
`request`	Yes	Natural language question. Include everything you need in one question — all channels, metrics, date ranges, and data sources. For example, "Give me website traffic from GA4, organic search performance from GSC, and paid search results from Google Ads for March 2026" is a single valid request. Never break a multi-part question into separate calls.
`end_date`	No	End date: YYYY-MM-DD or relative ('today', 'yesterday'). Defaults to yesterday.
`start_date`	No	Start date: YYYY-MM-DD or relative ('30daysAgo'). Defaults to 30 days ago.
`format_hint`	No	Optional — leave unset for almost all requests. The default synthesized answer is the correct, recommended output for anything a person will read. Only set this when the output will be parsed by software rather than read by a human (e.g. a chart, dashboard, or artifact needs structured data), never for a conversational answer. Example: "Return only valid JSON, no prose." Requesting JSON for a normal answer produces worse, more verbose results.
`source_hints`	No	Preferred data sources. If omitted, server auto-selects via semantic routing.
`reference_images`	No	URLs of reference images (logos, product photos, style references) for image generation

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJun 2, 2026

addedInput schema / properties / format_hint

Added value: +{
+  "description": "Optional — leave unset for almost all requests. The default synthesized answer is the correct, recommended output for anything a person will read. Only set this when the output will be parsed by software rather than read by a human (e.g. a chart, dashboard, or artifact needs structured data), never for a conversational answer. Example: \"Return only valid JSON, no prose.\" Requesting JSON for a normal answer produces worse, more verbose results.",
+  "type": "string"
+}

Changed1 schema field changedMay 22, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
First observedApr 14, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral insight: the server auto-routes internally to all needed sources and returns a combined response with same granularity as individual queries. This goes beyond annotations and helps the agent understand internal routing.

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?

The description is front-loaded with purpose and key instructions, but contains some redundancy (e.g., the single-call rule is mentioned twice). However, it is well-structured with clear sections for each parameter. A small reduction in repetition would make it more concise, but overall it is efficient for the amount of information conveyed.

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 complexity (7 parameters, no output schema, multiple data sources), the description addresses usage guidelines, parameter details, and edge cases (e.g., missing domain). It does not explain return format, but annotations and the 'combined response' hint partly compensate. Overall, it provides sufficient context for an AI 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.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage, so baseline is 3. However, the description significantly augments each parameter with practical usage details: domain includes when required and fallback advice, request emphasizes including everything in one question, dates include defaults and relative formats, format_hint explains when to set vs leave unset, source_hints describes auto-selection, and reference_images clarifies usage. This adds substantial meaning beyond the schema.

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's purpose: to query marketing data and analyze websites across multiple domains including analytics, SEO, advertising, etc. It distinguishes itself from siblings by emphasizing that a single call covers multiple data sources, and it contrasts with list_sources and research which have different scopes.

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?

Explicit guidelines are provided: always use a single call, do not split multi-source questions, call list_sources first if no domain is established, and ask the user when ambiguous. It also warns against setting format_hint for normal answers. These clearly indicate when and how to use the tool.

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

All Agentcy - Your AI Marketing Agent tools Inspect

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

Need Help?