OrgLines

Add receipt

add_receipt

File a purchase receipt in the caller's personal space (the fields may come from a receipt photo the person sent to the bot and confirmed). Provide 'date' (YYYY-MM-DD) and 'total'; 'merchant_name' is resolved/created case-insensitively to ONE merchant. Optional 'currency' (ISO 4217, default EUR), 'category' (groceries/household/transport/health/dining/entertainment/clothing/utilities/other), 'payment_method', 'document_id' (link a photo/pdf already uploaded to the caller's documents), 'notes', and 'items' (0..100 line items {name_raw, name_normalized, qty?, unit? pcs/kg/g/l/ml, unit_price, total}). When items are present the server checks sum(items.total) is within ±0.05 of the total: match → status 'confirmed', else 'needs_review'. Additive, the caller's own record, removable with delete_receipt — so it is written straight away rather than proposed. CONFIRMATION: this tool runs immediately when the caller asks for it — it writes only their own record, and they can undo it from this same surface, so the request is taken as the instruction. You get an ordinary result, not a plan_token. Everything destructive, outbound or financial still proposes and waits.

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": {
      "date": "<date>",
      "merchant_name": "<merchant_name>",
      "total": "<total>"
    },
    "name": "add_receipt"
  }
}

Input Schema

Name	Required	Description	Default
`date`	Yes
`items`	No
`notes`	No
`total`	Yes
`category`	No
`currency`	No
`document_id`	No
`merchant_name`	Yes
`payment_method`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare it is a non-destructive, non-open-world write; the description goes far beyond that by stating it writes immediately with no plan_token, is additive and undoable, resolves merchant_name case-insensitively to a single merchant, and validates sum(items.total) within ±0.05 to set status 'confirmed' vs 'needs_review'. That is exactly the behavioral detail an agent needs before invoking it.

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?

Purpose and required fields are front-loaded, followed by optional parameters, validation behavior, and confirmation semantics in a logical order. It is dense but long; the CONFIRMATION block restates the undo point twice ("removable with delete_receipt" and "they can undo it from this same surface"), which could be trimmed.

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 9-parameter mutation tool with no output schema and no annotations on permissions, the description covers inputs, validation outcome and confirmation policy thoroughly. The remaining gap is the shape of the returned record (e.g. the created receipt's id) beyond the 'confirmed'/'needs_review' status, which an agent may need for follow-up calls.

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 description coverage is 0%, so the description carries the full burden and does: date format YYYY-MM-DD, currency ISO 4217 with default EUR, the enumerated category list, document_id meaning (link a photo/pdf already in the caller's documents), and the 0..100 items structure with unit enum and per-item fields. This adds meaning well beyond the bare schema, including default values the schema does not encode.

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?

"File a purchase receipt in the caller's personal space" gives a specific verb (file), resource (purchase receipt) and scope (caller's own space). It is immediately distinguishable from update_receipt/delete_receipt siblings, and the parenthetical about a confirmed receipt photo adds realistic origin context.

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?

It explains the trigger condition (the caller asks for it, e.g. after confirming a receipt photo) and routes removal to delete_receipt. It also delineates when NOT to treat the call as a proposal: destructive, outbound or financial actions still propose and wait. No explicit contrast with update_receipt is given, so it falls short of a full 5.

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

All OrgLines 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?