Skip to main content
Glama

Re-dive an Existing Niche

redive_niche
Destructive

Refresh an existing niche’s Amazon research with current data by re-diving its competitors or discovering a new set; returns a dive ID to track completion.

Instructions

Use this to refresh an existing niche's research with current Amazon data, instead of creating a new niche with create_niche_dive. ⚠️ Spends dive tokens (one batch per ASIN dived) 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 re-dive — if a call errors or times out, poll get_dive_status instead of re-calling. Two modes: same_competitors re-dives the niche's current competitor set (no other argument needed) and discover finds a fresh set, sized by numberOfCompetitors and steerable with heroAsin / lockedAsins / excludedAsins. Runs asynchronously: returns a diveId and an estimatedCompletionDate — poll get_dive_status with that diveId until it reports success. The niche keeps its nicheId, so existing rank radars and reports follow the refreshed data.

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": {
      "nicheId": "<nicheId>",
      "mode": "<mode>"
    },
    "name": "redive_niche"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYesHow to pick the competitors for the refreshed dive. `same_competitors` re-runs the niche's current competitor set and takes no other argument — use it to refresh stale data. `discover` searches for a fresh competitor set, which is what you want when the niche has changed.
confirmNoMust be true to proceed — a re-dive spends dive tokens. Confirm the cost with the user first.
nicheIdYesThe niche to re-dive. Get one from `list_niches`.
heroAsinNo`discover` mode only. Seed product the competitor discovery starts from. Defaults to the niche's highest-selling competitor, preferring one the user's own connected seller account owns.
lockedAsinsNo`discover` mode only. ASINs that must stay in the competitor set regardless of what discovery finds. Cannot exceed `numberOfCompetitors`, and cannot overlap `excludedAsins`.
excludedAsinsNo`discover` mode only. ASINs discovery must never select. They are saved as exclusions on the niche, so every later dive of this niche skips them too. ASINs already excluded on the niche are always skipped; put one in `lockedAsins` to dive it anyway.
numberOfCompetitorsNoTotal ASINs the refreshed dive should contain, including `lockedAsins`. Required in `discover` mode and rejected in `same_competitors` mode. Dive tokens are spent per ASIN.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.21.0
    • changedInput schema / properties / excludedAsins / description
      Previous value: -"`discover` mode only. ASINs discovery must never select."New value: +"`discover` mode only. ASINs discovery must never select. They are saved as exclusions on the niche, so every later dive of this niche skips them too. ASINs already excluded on the niche are always skipped; put one in `lockedAsins` to dive it anyway."
  2. Addedv0.11.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes well beyond: token spend is per-ASIN batch, the action is irreversible, retries are unsafe and spawn duplicate re-dives, execution is asynchronous with `diveId`/`estimatedCompletionDate`, and the `nicheId` survives so rank radars and reports follow the new data. This is exactly the operational context an agent needs before a costly mutation.

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-loads the cost warning and the mode split, and every clause carries information. Slight redundancy in repeating that a call spends tokens and cannot be undone across the cost and retry sentences, and the paragraph is dense enough to need a second read, but nothing is filler.

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 a 7-parameter asynchronous mutation with no output schema, the description supplies what the structured data cannot: the return shape (`diveId`, `estimatedCompletionDate`), the polling loop via `get_dive_status` until `success`, and the post-condition that existing rank radars and reports carry over. Nothing needed to invoke it correctly is missing.

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 100%, so baseline is 3, but the description adds real meaning: `same_competitors` takes no other argument, `discover` is sized by `numberOfCompetitors` and steerable via `heroAsin`/`lockedAsins`/`excludedAsins`, and cost scales with ASIN count. It does not re-explain `confirm` or `nicheId`, whose schema text already covers them, so it is additive rather than duplicative.

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 (refresh an existing niche's research) and explicitly contrasts it with the sibling `create_niche_dive`, which creates new. The agent can pick correctly without opening either 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?

Gives explicit when-to-use (refresh instead of create), when-not (do not retry on error/timeout — poll `get_dive_status` instead), a precondition (set `confirm: true` only after user cost approval), and routes between the two modes: `same_competitors` for stale data, `discover` when the niche has changed.

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