Vera

Keyword Ideas

keyword_ideas

Read-only

Keyword ideas for a seed keyword from Google autocomplete (the seed plus question words or the alphabet), People Also Ask and related searches, cleaned and de-duplicated. Each idea carries its sources and an intent label (question, comparison, commercial, local, informational). Works in Arabic. Ideas only: no search volumes. Charged for the results page (7 credits live, 1 from your cache) plus 7 credits for each autocomplete call that returns suggestions, so at most 14 credits for expand 'none', 70 for 'questions' (the default), 196 for 'alphabet' (210 for an Arabic seed) and 217 for 'all'; it stops early once limit ideas are found, which is 12. Set fresh to true to search the results page live; autocomplete is always live. The most the call can cost is held first and you are charged for what it returns; a call that fails costs nothing.

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": {
      "seed": "<seed>"
    },
    "name": "keyword_ideas"
  }
}

Input Schema

Name	Required	Description
`gl`	No
`hl`	No
`seed`	Yes
`fresh`	No
`limit`	No
`expand`	No
`location`	No
`location_code`	No
`idempotency_key`	No	Optional. Send the same key (16 to 128 letters, digits, _ . : -) to retry this exact call safely: a retry within 24 hours returns the first result and is not charged again.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 21, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: per-call credit costs by expand mode, cache vs live behaviour, that autocomplete is always live, early termination on `limit`, pre-authorization of the maximum cost, and that failed calls are free. This is exactly the cost/latency/charging context an agent needs before invoking.

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?

A single front-loaded paragraph that opens with what the tool returns and what each idea carries, then layers cost detail. Dense but nearly every sentence carries operational weight; the credit enumeration is long yet decision-relevant.

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?

No output schema exists, and the description does cover the return shape (sources plus an intent label with enumerated label types). The only real gap is the undocumented locale/location parameters (gl, hl, location, location_code), which an agent must guess at.

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 coverage is only 11%, so the description carries the burden. It usefully documents expand values ('none', 'questions', 'alphabet', 'all'), fresh behaviour, and the early-stop semantics of `limit` — but gl, hl, location, location_code, and the seed itself get no explanation. It also states 'questions' and 12 as defaults where the schema declares null and 50, which muddies rather than clarifies.

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 verb+resource: keyword ideas for a seed keyword, and names the exact data sources (Google autocomplete, People Also Ask, related searches). It explicitly bounds the output ('ideas only: no search volumes'), which distinguishes it from volume/ranking-oriented siblings like google_serp or seo_audit.

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 concrete operating guidance: expand modes with their costs, the default mode, the early-stop at `limit`, and when to set fresh=true. It carves out scope ('no search volumes') but never explicitly routes to or away from a named sibling tool.

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

All Vera 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?