Skip to main content
Glama

Honeyfield Marketing MCP

DataForSEO: LLM top domains

dfs_llm_top_domains
Read-only

Domains, die bei diesen Keywords am haeufigsten als Quelle in KI-Antworten zitiert werden (max 10 Keywords, limit intern auf max. 10 gedeckelt) — speist die Off-Site-Ziel-Liste im GEO-Audit. platform: 'google' (Google AI Overview, Default) oder 'chat_gpt' — ein Call deckt genau eine Plattform ab; fuer beide zweimal aufrufen. Bei 'chat_gpt' liefert DataForSEO nur Daten fuer United States/Englisch, location/language werden dann automatisch auf 'United States'/'en' gesetzt (uebergebene Werte werden ignoriert). Pay-as-you-go (normaler DataForSEO-Zugang). location/language: Default aus dem Workspace; Format wie bei dfs_keyword_volume. Fehler kommen als Ein-Element-Liste [{error, ...}] (api_error/task_error, dfs_timeout, dfs_unreachable, invalid_platform) — vor der Auswertung auf 'error' pruefen. workspace: Slug des Kunden-Workspace (optional bei nur einem Workspace).

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": {
      "keywords": "<keywords>"
    },
    "name": "dfs_llm_top_domains"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
keywordsYes
languageNo
locationNo
platformNogoogle
workspaceNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnly/openWorld, yet the description discloses rate/size caps (max 10 keywords, limit capped at 10), platform-specific data restrictions, silent overriding of location/language for chat_gpt, pay-as-you-go billing, and a full error envelope with named error codes (api_error, dfs_timeout, dfs_unreachable, invalid_platform) plus the instruction to check for 'error' before evaluating. That is substantial context beyond the annotations and consistent with readOnlyHint=true.

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?

Dense but front-loaded: what it returns, then platform behavior, then defaults, then error handling. Every line carries information, though the telegraphic line-broken style and mixed German/English key names add parsing friction for a mostly-English tool surface.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-param, one-required-param read tool with an output schema, the description covers the gaps the schema cannot: platform semantics, per-platform data limits, defaults sourcing, billing model, and error shape. Return values are legitimately delegated to the output schema.

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 0% across 6 params, so the description must carry it — and it largely does: platform values and their behavior, location/language defaults plus a format pointer to dfs_keyword_volume, workspace's optionality when only one exists, and the 10-keyword input cap. It misses the `limit` discrepancy (schema default 20 vs. 'internally capped at 10'), which is exactly the kind of collision an agent needs resolved.

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?

States a concrete resource and outcome: the domains most frequently cited as sources in AI answers for a given keyword set, and ties it to a downstream use (the off-site target list in the GEO audit). The verb is implied rather than stated, and no sibling (e.g. dfs_llm_mentions, dfs_llm_responses, dfs_llm_mentions_metrics) is named for contrast, so it stops short of a 5.

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?

Gives actionable routing rules: one call covers exactly one platform, so call twice for both, and 'chat_gpt' is restricted to US/English. It also caps keyword input at 10. What it lacks is explicit when-not guidance relative to the adjacent dfs_llm_* siblings, which an agent choosing between them would want.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources