Skip to main content
Glama

MyProduct: Create AI Mapping Task

start_ai_product_mapping
Destructive

[Store Products] [What it does] Starts an asynchronous AI Mapping computation between one DSers product and one supplier candidate; it does not apply the resulting mapping. [When to use] Use after the merchant selects a supplier candidate for that product. [When not to use] To find or compare candidates, use search_ai_mapping_candidates; this tool cannot apply a computed mapping — that requires the mapping-apply tool associated with get_store_product_mapping. [How to use] Copy dsers_product_id from list_managed_store_products; copy supplier_platform_id and supplier_product_id from the same search_ai_mapping_candidates candidate. Read task_created and next_step before acting: a newly created task has task_created=true; a false value can point to an existing task, an existing completed result to apply, or an Applied result requiring confirmed remap. Follow the returned status_tool only when present, using its task_type and task_id; do not treat running status as completion. [Side effects] A response with task_created=true consumes 8 AI Credits and creates a computation task; history-only responses create nothing, consume no Credits, and leave the product mapping unchanged. [Confirmation] Requires explicit, non-skippable confirmation; show the exact product, candidate, and 8 AI Credits cost first. [Follow-up] Follow next_step: poll an indicated new or existing task until terminal, apply an indicated completed result only after its separate confirmation, or show the remap preview before calling again with remap=true.

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": {
      "dsers_product_id": "<dsers_product_id>",
      "supplier_platform_id": "<supplier_platform_id>",
      "supplier_product_id": "<supplier_product_id>"
    },
    "name": "start_ai_product_mapping"
  }
}

Input Schema

NameRequiredDescriptionDefault
remapNoSet true only after the latest Candidate Search shows StatusApply for this exact candidate and the user explicitly confirms the displayed Applied remap preview. It creates a new AI Mapping computation and does not apply a Mapping.
countryNoDestination country for the AI Mapping task. Copy the same country used as ship_to in the prerequisite Candidate Search; defaults to US.US
dsers_product_idYesCopy from items[].dsers_product_id in list_managed_store_products results. Required.
supplier_product_idYesCopy from supplier_product_id in search_ai_mapping_candidates results. Required.
supplier_platform_idYesCopy from supplier_platform_id in search_ai_mapping_candidates results. Required.

Output Schema

NameRequiredDescriptionDefault
statusYesInitial normalized task status
countryYesDestination country used by AI Mapping
historyYesLatest matched candidate job ID, progress, and application status when present
messageYesHuman-readable task outcome
task_idYesProduct BFF AI Mapping task ID as a decimal string
acceptedYesWhether Product BFF accepted the AI Mapping task
next_stepYesMachine-readable next action
operationYesStarted business operation
task_typeYesTask type to pass to status_tool
status_toolYesTool used to poll this task
task_createdYesWhether this call created a new AI Mapping task
history_countYesNumber of prior jobs included; currently zero or one latest candidate job
history_foundYesWhether the exact matched candidate returned a latest AI Mapping job
dsers_product_idYesSource DSers My Product ID as a decimal string
poll_after_secondsYesRecommended delay before polling
supplier_product_idYesSelected supplier product ID
supplier_platform_idYesSelected supplier platform ID as a decimal string
toolcall_response_atYesUTC timestamp when the Tool response was returned, formatted as RFC3339.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds material context the annotations cannot convey: task_created=true consumes 8 AI Credits, history-only responses create nothing and leave mapping unchanged, and explicit non-skippable confirmation is required. It stops short of describing failure modes or what happens on duplicate concurrent calls, so it is not fully exhaustive.

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?

Bracketed section labels (What it does / When to use / When not to use / Side effects / Confirmation / Follow-up) make it scannable and the scope statement is front-loaded. It is long and the How-to-use paragraph partly repeats the schema's copy-from guidance, which costs a little.

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?

Given a mutating, credit-consuming, asynchronous tool with an output schema, the description covers cost, confirmation, the meaning of task_created/next_step/status_tool, and the remap path. Nothing an agent needs to call it correctly or interpret the result 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 the baseline is 3, but the description adds workflow meaning beyond the schema by tying the remap flag to a remap preview shown before calling again and by referencing the same candidate used in the prerequisite search. The country parameter is not addressed in prose, but the schema documents it.

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: starts an asynchronous AI Mapping computation between one DSers product and one supplier candidate, and explicitly bounds it with 'it does not apply the resulting mapping'. This cleanly separates it from search_ai_mapping_candidates and the apply-mapping siblings.

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?

Has explicit When to use ('after the merchant selects a supplier candidate for that product') and When not to use, naming the alternative tool for finding/comparing candidates and the apply tool needed to actually apply a mapping. The follow-up section further routes the agent to polling or applying.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.