Skip to main content
Glama
Sign In

Sightkick

by so.sightkick
OverviewDiscussionsAdmin

Research backlinks

research_backlinks

Other sites' links, from the backlink index: one of the month's backlink lookups per call (an answer from the last 7 days is free unless refresh, and usage says what's left). The site's own profile is get_backlinks profile, free. lookup:

  • profile(domain, refresh?): Who links to a site: domain rating, links, referring sites, spam score, the 25 strongest.

  • gap(rivals, refresh?): Pages linking to every rival named (one to three) and not to the site, strongest first: pitch them with update_outreach add.

  • metrics(targets): Link metrics for up to 50 domains or pages.

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": {
      "lookup": "<lookup>"
    },
    "name": "research_backlinks"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainNoA domain or a page
lookupYes
rivalsNo
refreshNo
targetsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the metering model that explains the non-read-only hint: one monthly lookup per call, a cached answer from the last 7 days is free unless refresh is set, and usage reports what's left. It does not say what happens when quota is exhausted or how errors surface, so it stops short of 5.

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?

The quota/cost sentence is correctly front-loaded and the 'lookup:' bullet list keeps the three modes scannable. Some parenthetical nesting ('an answer from the last 7 days is free unless refresh, and usage says what's left') is dense enough to need a second read.

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?

With no output schema, the description carries return-shape duty and does deliver it: profile returns domain rating, links, referring sites, spam score and the top 25; gap returns ordered page lists; metrics returns link metrics. What's missing is the quota-exhausted path and confirmation of parameter-to-mode applicability.

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 only 20% (just domain: 'A domain or a page'), so the description must compensate and largely does: it defines all three lookup enum values, the 1-3 rival constraint for gap, the 50-target bulk scope for metrics, and refresh as the cache-bypass. It never states which parameters pair with which mode (domain with gap, etc.), leaving that inference to the agent.

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 resource (other sites' links from the backlink index) and immediately bounds scope against a sibling: 'The site's own profile is get_backlinks profile, free.' The three lookup modes are then enumerated by name, so an agent can map intent to tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Each mode carries its own when-to-use: profile for who links to a site, gap for pages linking to 1-3 rivals but not the site, metrics for bulk link stats on up to 50 domains/pages. It even routes a follow-on action ('pitch them with update_outreach add'), which is explicit alternative selection rather than implied usage.

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