Rillow

Find keywords

find_keywords

Keyword ideas with monthly search volume, difficulty (0-100) and intent, for the project's country. With a seed, returns suggestions around it (fetched once per seed, then saved). Without a seed, returns the keywords the site already ranks for, with position and URL, which are the quickest wins in positions 4 to 20, plus suggestions saved from earlier seeds. Each suggestion has the average domain rating and linking sites of its top 10 pages (compare them with site_domain_rating), the change in searches over a year, and peak_month when it is seasonal. When DataForSEO has fewer than 10 ideas for a seed, Google's own suggestions come too. Keywords already in the plan are marked in_plan, and keywords the user marked Not for us are left out. Volume, difficulty and positions are DataForSEO estimates, not Google's own numbers. Read the top results with get_serp before you plan a page for a keyword.

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": "find_keywords"
  }
}

Input Schema

Name	Required	Description
`seed`	No	A topic or keyword to expand
`limit`	No	How many keywords, 25 by default
`intent`	No	Search intent
`min_volume`	No	Minimum monthly searches
`project_id`	No	Project id from list_projects. Leave it out when the user has one project.
`position_max`	No	Without a seed: highest position
`position_min`	No	Without a seed: lowest position
`max_difficulty`	No	Maximum difficulty, 0-100

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With readOnlyHint=false declared, the description carries the extra burden of explaining the side effect, and it does: suggestions are fetched once per seed and then saved, and earlier seeds' suggestions are returned later. It adds filtering rules (Not for us keywords excluded, in_plan marked), a data-provenance caveat (DataForSEO estimates, not Google's numbers), a fallback behavior (Google suggestions when DataForSEO returns <10 ideas), and seasonal/peak_month fields — none of which the annotations 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-loaded with the primary output, then the seed/no-seed split, then caveats and the get_serp next step — a sensible priority order. It is dense and slightly run-on in the middle, but every sentence adds information an agent would otherwise lack.

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 open-world, 8-parameter tool with no output schema, the description covers return contents well: volume, difficulty, intent, position/URL, domain rating and linking sites of top-10 pages, yearly search change, peak_month, in_plan flags. Only the distinction from closely named siblings (get_keyword_metrics, get_ranked_keywords) is left implicit.

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 100%, so baseline is 3, but the description adds real meaning: it explains that position_min/position_max only apply in the no-seed mode and what that mode returns, and that max_difficulty and intent are idea filters. The seed field's caching semantics ('fetched once per seed, then saved') give behavior the schema cannot express.

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 resource (keyword ideas) with the fields returned (volume, difficulty 0-100, intent) scoped to the project's country. It clearly separates the two modes — seed expansion vs. keywords the site already ranks for — so an agent knows exactly which behavior it's getting. It also names related tools (get_serp, site_domain_rating) instead of leaving the agent to guess.

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?

Explicitly tells the agent when to pass a seed (expand around a topic) and when not to (find existing ranking keywords / quick wins in positions 4-20), plus a follow-up step: read top results with get_serp before planning a page. It stops short of contrasting itself with sibling tools like get_keyword_metrics or get_ranked_keywords, which would make the routing decision fully unambiguous.

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

All Rillow 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?