Skip to main content
Glama
dylanpakd-cyber

creator-growth-intel

search_claims

Search operator-backed claims on creator pricing, sourcing, and app growth, each with verbatim quotes and source links. Returns explicit no-coverage notice when evidence is thin.

Instructions

Search receipt-backed claims from operators who publicly describe how they run creator programs, UGC, influencer buys and app growth. Use it for how to price a creator, where to source them, how to brief them, what to test, what failed. Every result carries a verbatim quote and a working permalink to the author. Returns an explicit no-coverage notice when the corpus does not address the question, which you should relay rather than filling the gap.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
railNoTHE MOST IMPORTANT FILTER FOR ANY RATE QUESTION. The word CPM names four unrelated economies here and pooling them inverts the answer. BUY is a brand or agency paying a creator per 1,000 delivered, and is the only set comparable to what a brand would pay. PLAT is a PLATFORM paying a creator out of ad revenue (YouTube AdSense RPM, TikTok Creator Fund, Reels bonuses), a different market entirely, and it is roughly a third of all rate-bearing claims. ADBENCH is what Meta or programmatic ads cost per 1,000. REV is revenue earned per 1,000, a ceiling on what you can afford to pay. Pass rail:'BUY' whenever you are asking what someone pays a creator.
limitNoDefault 12, capped at 50
nicheNoWhich harvest sweep the evidence came from. This is PROVENANCE, not a content vertical: 'micro-pricing' is the rate and CPM sweep, not a finance sweep, and a claim about any vertical can sit in any slice. 'adjacent-niche' is the fintech, investing, edtech and gaming sweep. 'app-scaling' is the YouTube long-form sweep. 'creator-ops' and 'operator-timeline' are general creator-program evidence drawn mostly from health, ecommerce and beauty.
queryYesNatural language or keywords
topicNoRestrict to one topic tag, e.g. pricing, sourcing, hooks-and-scripting
buy_typeNoWithin the BUY rail, what kind of buy. This moves the median by more than an order of magnitude, so a figure blended across buy types is meaningless. KOL is one sponsored post from an existing audience, priced as a fee. PROGRAM is a managed roster of briefed creators paid a set rate per thousand. CLIP is an open per-1,000 bounty on clips, usually capped per post. AMPLIFY is whitelisting or spark ads. AGENCY is an intermediary's pass-through price inclusive of margin.
operatorNoRestrict to one handle, without the @
claim_typeNo
Behavior5/5

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

With no annotations, the description fully discloses behavior: every result carries a verbatim quote and a working permalink, and the tool returns an explicit no-coverage notice when the corpus lacks an answer, with instruction to relay rather than fabricate. This goes well beyond the bare minimum and helps the agent set expectations.

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

Conciseness5/5

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

The description is only three sentences, front-loaded with the core purpose and use cases. Every sentence earns its place—purpose, usage, and critical output/behavior—with no redundancy or 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?

Considering 8 parameters, no output schema, and no annotations, the description covers purpose, output characteristics, and the no-coverage edge case, which is substantial. It could be slightly more complete by explaining how search results relate to sibling tools or when coverage stats might be the more appropriate tool, but overall it is adequate for a complex search 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 description coverage is 88% (baseline 3), and the schema already provides deep semantics for 'rail' and 'buy_type'. The description adds no parameter-specific meaning beyond what the schema offers, so it does not elevate the score.

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?

Specific verb+resource: 'Search receipt-backed claims from operators...' and enumerates concrete use cases ('how to price a creator, where to source them, how to brief them, what to test, what failed'). The tool is clearly differentiated from siblings (coverage_for, corpus_stats) by its focus on searching for evidence rather than reporting coverage or stats.

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?

Explicitly states when to use the tool: 'Use it for how to price a creator, where to source them, how to brief them, what to test, what failed.' However, it does not mention alternatives or situations where a sibling tool would be preferred, so it misses explicit exclusion guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dylanpakd-cyber/creator-growth-intel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server