Skip to main content
Glama
Sign In

Tokfluence

by com.tokfluence
OverviewDiscussionsAdmin

Mine seed hashtags for a niche

suggest_campaign_keywords
Read-onlyIdempotent

Finds the hashtags creators in a niche actually post under, measured against the index. Use it before create_seed_campaign, always, and use it when a search comes back thin to find the words you should have searched for.

Guessed tags are reliably worse than mined ones. The tags a marketer writes down are the ones a marketer would search; the tags creators use are usually narrower and more specific, and they are what a crawl needs to follow.

It also tells you which tags are too broad to seed with. A tag on hundreds of thousands of creators steers nothing: the crawl drowns in general content.

Costs 1 credit per call. Refunded when mining is unavailable.

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": {
      "niche": "<niche>"
    },
    "name": "suggest_campaign_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many tags to return, 1-50. Default 25.
nicheYesThe niche in plain words, e.g. 'bladder health and pelvic floor'. Matched against creator bios.
regionsNoISO-3166 alpha-2 codes to mine within, e.g. ['US']. Optional; tags are largely global.
seed_hashtagsNoTags you already believe fit, without '#'. Anchors the result when the bio wording alone is loose.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing cost (1 credit per call), the refund condition, and that broad tags are flagged as unusable for seeding. What it omits is a precise statement of the response shape beyond implied tag-plus-breadth data, which matters somewhat given no output schema exists.

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?

Purpose and usage routing are front-loaded in the first two sentences, followed by supporting rationale. The mid-section explaining why mined tags beat guessed tags is persuasive but slightly longer than strictly necessary; still, each paragraph contributes a distinct point (why, and the broad-tag warning).

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?

Given no output schema, the description should convey what comes back, and it does so partially: a set of mined tags plus flags on tags too broad to seed with. It stops short of describing the concrete response structure or how the breadth signal is expressed, which is a minor gap for a read-only, credit-costing tool.

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 100%, so parameters are already well documented within the schema itself. The description adds conceptual framing about mined vs. guessed tags that indirectly touches seed_hashtags, but says nothing about limit or regions and adds no syntax or format detail beyond the schema. Baseline 3 applies.

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 and resource: finds the hashtags creators in a niche actually post under, measured against the index. This is clearly distinguishable from siblings like search_creators (creator discovery) and create_seed_campaign (campaign creation), which it explicitly positions itself upstream of.

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?

Gives explicit when-to-use instructions: 'Use it before create_seed_campaign, always' and 'when a search comes back thin to find the words you should have searched for.' It names the sibling alternative and the triggering conditions, leaving little to inference.

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

All Tokfluence 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