Aalto

Update products

aalto_update_products

DestructiveIdempotent

Changes fields, tags or a collection status on up to 50 products. Always preview first (dry_run true, the default): it writes nothing and returns every change plus a confirm_token. Show the user the changes, then call again with dry_run false, the same arguments, the confirm_token and a new idempotency_key. If anyone edits these products in between, the commit is refused; preview again.

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": {
      "product_ids": "<product_ids>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "aalto_update_products"
  }
}

Input Schema

Name	Required	Description
`set`	No	Fields to overwrite on every listed product; null clears a field.
`tags`	No	Tag names to add or remove (≤10 each). Personal or Team plan.
`status`	No	Set the status of these products in one collection they belong to.
`dry_run`	No	true (default) previews the changes and returns a confirm_token. Show the user, then call again with dry_run false and that token.
`product_ids`	Yes	1–50 product ids in this workspace.
`confirm_token`	No	Required when dry_run is false: the token from a preview of exactly the same request (valid 10 minutes, single use).
`idempotency_key`	Yes	Required. A new unique string per intended change (8–128 chars). Retrying with the same key and same arguments replays the first result instead of writing twice.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only say destructive/idempotent/not-read-only; the description adds the material behavior: preview writes nothing, the commit is bound to exactly the same arguments, and a concurrent edit causes the commit to be refused rather than silently overwriting. That optimistic-concurrency guarantee is the key risk fact an agent needs before calling a destructive bulk write.

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?

Four short sentences, front-loaded with what changes and the safe default, then the commit procedure and the failure case. No restatement of the title 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?

Covers the multi-step write flow and concurrency risk for a 7-parameter tool with nested objects and no output schema. Minor gaps: it does not say what a successful commit returns or whether the 50-product batch is all-or-nothing on partial failure.

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 parameters are already documented individually; the description adds the cross-parameter contract (dry_run false requires the same arguments, the prior confirm_token, and a *new* idempotency_key). It does not explain the semantics of set/tags/status beyond the schema, but that is already covered.

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 (changes) plus the exact mutation surfaces (fields, tags, collection status) and a hard scope (up to 50 products). This cleanly separates it from aalto_create_products and aalto_move_products without needing to name them.

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?

Gives an explicit two-phase protocol: always preview with dry_run true, show the user, then commit with the same arguments plus confirm_token and a new idempotency_key. It also states the recovery path when a concurrent edit causes refusal. It stops short of routing between this tool and siblings like aalto_move_products or aalto_organize for overlapping changes.

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

All Aalto tools Inspect

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

Need Help?