Aalto

Start a spreadsheet import

aalto_import_start

Idempotent

Starts importing a CSV of products into a private collection: returns a job_id and, for csv_upload, a signed URL to PUT the file to (valid 2 hours). Nothing is imported yet: next call aalto_import_preview, show the user the result, then aalto_import_commit. CSV only (convert XLSX first), up to 5 MB and 2,000 rows. At most 10 open (not yet committed) imports per person in each workspace; the limit is best effort.

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": {
      "collection_id": "<collection_id>",
      "source": "<source>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "aalto_import_start"
  }
}

Input Schema

Name	Required	Description
`csv`	No	Only with source inline: the CSV text (≤1,000,000 characters). Convert XLSX to CSV first.
`source`	Yes	csv_upload (default choice): you PUT the file to a signed URL. inline: pass small CSV text in csv.
`collection_id`	Yes	A private collection in this workspace to import into (the Library is fine).
`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

A4.9/5.0

Behavior5/5

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

Annotations cover the safety/idempotency profile, and the description adds non-obvious behavior: the signed URL is valid only 2 hours, the call is a staging step that imports nothing, and there is a best-effort cap of 10 open imports per person per workspace. Those are exactly the traits an agent needs and cannot get from the structured fields.

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?

Front-loads the core action and return value, then the required call sequence, then the constraints. Three dense sentences with no filler or repetition.

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?

No output schema exists, yet the description names the return payload (job_id, signed URL) and its lifetime, plus all limits an agent must respect before calling. Complete for a mutation-style staging tool.

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; the description still adds value by explaining the csv_upload-vs-inline choice, the 5 MB / 2,000-row ceiling, and how idempotency replay behaves. It does not add syntax detail beyond the schema, so it lands just above baseline.

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 plus resource ('Starts importing a CSV of products into a private collection') and it explicitly names the two follow-up siblings, aalto_import_preview and aalto_import_commit, so the agent can separate this from them. It also states what is returned (job_id, signed URL).

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 the ordered workflow (start → preview → show user → commit), names the alternatives (csv_upload vs inline are spelled out in the schema; XLSX must be converted first), and states hard exclusions ('Nothing is imported yet', 'CSV only'). No inference needed.

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?