Skip to main content
Glama
Sign In

Sightkick

by so.sightkick
OverviewDiscussionsAdmin

Research keywords

research_keywords

Keyword research, each with volume, difficulty, CPC, intent, Opportunity (0 to 100), fit (0 to 3), onTopic and saved. One keyword search per call (the same within 30 days is free). Save the good ones with update_keywords. from:

  • seed(query, limit?, months?): Ideas around a seed search.

  • competitor(domain, limit?, months?): The searches a site ranks for (any domain, the top 200), with its position.

  • gap(domain, limit?, months?): Searches a rival ranks for and the site doesn't.

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": {
      "from": "<from>"
    },
    "name": "research_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromYes
limitNo
queryNo
domainNo
monthsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses the credit/caching behavior — one keyword search per call and repeats within 30 days are free — which explains why a research call is flagged non-read-only. It does not cover failure modes or whether the 30-day cache applies across modes.

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 purpose and cost, then a scannable per-mode list. The opening field enumeration is dense but earns its place because there is no output schema; the credit note could sit slightly earlier but nothing is filler.

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 5-parameter, multi-mode research tool with no output schema, the description covers return fields, mode routing, cost, and the follow-up write tool. Only the 'months' semantics and limit defaults remain unclear, which are minor against what is supplied.

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?

With 0% schema coverage, the description carries the burden and does well: it maps query to seed, domain to competitor/gap, and marks limit and months as optional per mode. The one real gap is the boolean 'months' parameter, whose meaning is never explained, and limit's default/maximum is left to 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 states a specific verb+resource (keyword research) and immediately enumerates what each row carries (volume, difficulty, CPC, intent, opportunity, fit, onTopic, saved), which separates it from the sibling get_keywords (saved-keyword retrieval) and points to update_keywords for persistence.

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?

It gives explicit conditions for each of the three sourcing modes (seed = ideas around a query, competitor = what a domain ranks for, gap = rival-only searches) and redirects saving to update_keywords. It stops short of saying when not to use this tool, e.g. versus get_keywords for already-researched terms.

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

All Sightkick toolsInspect
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