Hook Detector

research_keywords

Keyword research for YouTube. volume: always estimated (YouTube publishes no search counts): estimated_monthly_searches with a range, a 0 to 100 score and band, its source (Google Trends with the YouTube filter against fixed anchors; or, when Trends is busy, YouTube autocomplete and the top results' views) and basis. competition: 0 to 100 counted from the top 10 long-form results (big channels, posted in the last year, the keyword in the title, how many beat their own channel 2x). score: value 0 to 100 (60% volume, 40% the room competition leaves), band very_low, low, medium, high or very_high (vidIQ's brackets) and the basis naming its inputs. related, questions, rising: terms from autocomplete and the top results' titles, each with its source. Costs 2 credits, refunded when the read fails; a bad request is 422 and costs nothing. Takes about 10 to 30 seconds. Same as POST /v1/keywords. Read it back with get_call.

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": "research_keywords"
  }
}

Input Schema

Name	Required	Description
`api_key`	No
`country`	No	a two-letter country code, default US
`keyword`	No	the words people would type into YouTube search, 2 to 100 characters
`language`	No	a two-letter language code for the autocomplete, default en
`idempotency_key`	No	1 to 255 visible ASCII characters; the same key and request within 24 hours answer the saved remix and charge nothing; the same key with another request is 422 idempotency_key_reused

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 26, 2026

TDQS

A3.6/5.0

Behavior5/5

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

No annotations exist, and the description carries the full burden well: it states the 2-credit cost, refund on read failure, that a 422 bad request is free, the 10-30 second latency, and that it mirrors POST /v1/keywords. That is exactly the cost/latency/error context an agent needs before calling a billed, slow operation.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is a dense run-on of nested parentheticals about output fields that the output schema already documents. Operational facts (cost, failure, latency) are buried at the very end where they matter most for a billed call.

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 a slow, credit-consuming tool with no annotations and a full output schema, the description covers cost, refund behavior, error semantics, latency and the equivalent REST endpoint. The notable gap is that it never mentions the api_key parameter or auth expectations.

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 80%, so the schema already documents country, keyword, language and the idempotency key; the description adds nothing about these parameters. Its lengthy coverage of volume/competition/score fields describes return values, which the existing output schema already specifies.

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?

Opens with a specific verb and resource: 'Keyword research for YouTube', then enumerates the exact artifacts returned (volume, competition, score, related/questions/rising). An agent knows precisely what it gets. It never contrasts itself with siblings like search_index or niche_report, 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 Guidelines2/5

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

Provides no when-to-use, when-not, or alternative-tool guidance relative to the many sibling tools (search_index, niche_report, trending_shorts). The only workflow hint is the trailing 'Read it back with get_call', which is a post-call step, not selection guidance.

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

All Hook Detector 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?