Sorsa

configure_prep_sheet

Configure the prep sheet. enabled turns auto-push to the user's own Google Sheet on/off: every new purchase (web app, MCP add_purchase, or the Discord 🛒 button) is appended as a row to tab_name (default 'Prep Sheet'). columns is the user's prep centre's column headers IN ORDER — free text, exactly as they appear on the sheet. Known headers are synonym-matched to purchase fields (Date, Item/Title, ASIN, SKU, Qty, Cost, Total Cost, Sale Price, Profit, ROI, Store/Company, Sourced From, Sales Rank, Monthly Sales, Notes, Image URL); unknown headers (e.g. 'Order Number') become empty columns the prep centre fills in. This is the SAME column config as the Items Purchased page's Prep Sheet Settings and the daily DM CSV, so changing it here changes all three. Omitted arguments keep their current values. The push also needs their Google Sheet connected (get_sheet_status) with an 'append_row' action in their Apps Script — if the response shows sheet_connected false, tell them to connect it in Sorsa Settings first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "configure_prep_sheet"
  }
}

Input Schema

Name	Required	Description	Default
`columns`	No
`enabled`	No
`tab_name`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the downstream effect (every new purchase from web app, MCP add_purchase, or Discord button is appended), that unknown headers become empty columns, that the config is shared across three surfaces, and how to handle a sheet_connected=false response. This is exactly the behavioral context an agent needs before calling a 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-loaded with the core effect, then parameters in schema order, then the connectivity caveat. The known-header list is long but genuinely informative. Slightly dense in places, though no sentence is disposable.

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?

For a three-parameter mutation with no annotations and no output schema, the definition covers side effects, defaults, prerequisites, and error handling. It could go one step further by naming get_prep_sheet_config as the read counterpart or stating what a successful response contains beyond sheet_connected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description compensates fully: `enabled` is defined as an auto-push toggle, `tab_name` has its documented default 'Prep Sheet', and `columns` is described as ordered, free-text headers exactly as they appear on the sheet, with synonym-matching to purchase fields and empty-column fallback for unknowns. Ordering and format constraints are both made explicit.

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 (configure the prep sheet) and immediately decomposes the three configurable aspects: auto-push enablement, target tab, and column layout. An agent knows exactly what this tool mutates and what each argument means without opening the schema.

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?

Explains the operational context well: omitted arguments keep current values (partial-update semantics), and it flags the prerequisite that the user's Google Sheet must be connected with an 'append_row' action. It stops short of explicitly routing reads to the sibling get_prep_sheet_config, leaving that pairing implicit.

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

All Sorsa 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?