Skip to main content
Glama
Data-Dive-Tools

DataDive MCP

Official
by Data-Dive-Tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create a Niche Dive

create_niche_dive
Destructive

Start a new niche research dive from a seed ASIN, analyzing competitors asynchronously to generate a niche. Requires confirmed token cost; poll get_dive_status with the returned diveId for results.

Instructions

Use this to start new niche research from a seed ASIN. ⚠️ Spends dive tokens (cost scales with numberOfCompetitors) and cannot be undone — set confirm: true only after the user approves the cost. Not safe to retry: each call spends tokens again and starts a separate dive — if a call errors or times out, poll get_dive_status (or check list_niches) instead of re-calling. The dive runs asynchronously: this returns immediately with a diveId and an estimatedCompletionDate. Poll get_dive_status with that diveId until it reports success (which carries the new nicheId for use with list_niches, get_niche_keywords, etc.). Requires marketplace, asin, and numberOfCompetitors (min 2). After a Fast Keywords run for the same product, pass its requestId as fastKeywordsRequestId to link the dive to it.

Input Schema

NameRequiredDescriptionDefault
asinYesThe seed ASIN to start the dive from (e.g. B08N5WRWNW). Competitors are built around it.
confirmNoMust be true to proceed — creating a dive spends dive tokens. Confirm the cost with the user first.
marketplaceYesAmazon marketplace of the seed ASIN. Note these are full domain suffixes: com, ca, co.uk, com.mx, in, fr, de, es, it, co.jp (e.g. UK is `co.uk`, not `uk`).
numberOfCompetitorsYesHow many competitors to analyze (minimum 2). More competitors = deeper niche but more dive tokens.
fastKeywordsRequestIdNoLinks the dive to a Fast Keywords run for the same product: the `requestId` returned by `run_fast_keywords` or `refresh_fast_keywords`. Leave unset for a dive that follows no Fast Keywords run.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.20.1
    • addedInput schema / properties / fastKeywordsRequestId
      Added value: +{
+  "description": "Links the dive to a Fast Keywords run for the same product: the `requestId` returned by `run_fast_keywords` or `refresh_fast_keywords`. Leave unset for a dive that follows no Fast Keywords run.",
+  "minimum": 1,
+  "type": "integer"
+}
  2. First observedv0.8.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare destructiveHint=true; the description goes well beyond by quantifying the cost model (token spend scales with `numberOfCompetitors`), declaring irreversibility, warning that retries spend tokens again and fork a separate dive, and explaining the async contract (immediate `diveId` + `estimatedCompletionDate`, poll until `success` yields `nicheId`). This is precisely the operational context annotations cannot carry.

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 the cost/irreversibility warning, then retry safety, then the async lifecycle — a well-prioritized order. The 'Requires `marketplace`, `asin`, and `numberOfCompetitors` (min 2)' sentence is redundant with a fully-covered schema and could be cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async, destructive, token-spending mutation with no output schema, the description covers the full lifecycle: what it costs, what it returns, how to poll, what the terminal state gives you, and which downstream tools consume the result. An agent can invoke and follow up correctly without further information.

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 the schema already documents all five parameters including the `fastKeywordsRequestId` linkage and the `marketplace` enum caveat. The description adds only the cost-gating rationale for `confirm` and restates the required set, which is useful emphasis but largely duplicative of structured data.

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?

States a specific verb and resource — 'start new niche research from a seed ASIN' — which the agent can tell apart from list/get tools. It doesn't name the closest siblings (`create_niche_dive_from_competitors_list`, `redive_niche`), so the differentiation from those two is left implicit in the 'seed ASIN' phrasing.

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?

Explicitly says when to use it (new research from a seed ASIN, optionally after a Fast Keywords run) and when NOT to retry it, routing the agent to `get_dive_status` or `list_niches` on error or timeout. It also gates invocation on user approval of cost via `confirm: true`, leaving nothing to inference.

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

Deploy Server

Other Tools