Skip to main content
Glama

List expenses

crunch_list_expenses
Read-only

List expenses newest first and filter by supplier, type, date, payment method, or receipt status; view amounts, balances, and payment details, with paging or all results.

Instructions

List expenses (purchases, receipts and bills), newest first, filtered by supplier, expense type, date, payment date, payment method or whether a receipt is attached. Each result shows supplier, amounts, status, outstanding balance and payment method. Paged (up to 200 per page); use all=true to fetch every page.

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": "crunch_list_expenses"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoFetch every page (up to max_items) instead of a single page
rawNoReturn the full objects from the API instead of compact summaries (larger)
pageNoPage to fetch, starting at 0 (default 0)
sizeNoResults per page, up to 200 (default 50)
sortNoSort order as field,asc or field,desc, for example postingDate,desc
limitNoMaximum number of items
fieldsNoKeep only these fields (dot paths, such as supplier.companyName)
searchNoCase-insensitive substring match on any value
end_dateNoExpenses dated on or before (YYYY-MM-DD)
max_itemsNoWith all=true, stop after this many results (default 1000, at most 10000)
start_dateNoExpenses dated on or after (YYYY-MM-DD)
supplier_idNoOnly this supplier's expenses
expense_typeNoOnly this expense type, for example TRAVEL_AND_SUBSISTENCE
has_attachmentNoOnly expenses with (true) or without (false) a receipt attached
payment_methodNoOnly expenses paid this way, for example EFT
payment_end_dateNoPaid on or before (YYYY-MM-DD)
payment_start_dateNoPaid on or after (YYYY-MM-DD)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=true, openWorldHint=false, idempotentHint=false), the description discloses default ordering ('newest first'), page size cap (200), and the all=true fetch-everything behavior, which materially changes how an agent should page. It omits any note on permissions, large-result cost, or the interaction between all and max_items, so it is useful but not fully transparent.

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?

Two dense sentences with no filler: scope and filter dimensions first, then what results contain, then pagination behavior. Every clause carries information an agent needs before calling.

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?

With 17 parameters, no output schema, and a read-only list, the description correctly compensates by listing the returned fields (supplier, amounts, status, outstanding balance, payment method) and the paging model. It does not explain how search/fields/raw/limit compose with each other, which leaves a small gap for a tool with this many knobs.

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

Parameters3/5

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

Schema description coverage is 100%, so all 17 parameters are already documented, establishing a baseline of 3. The description adds only two pieces of meaning beyond the schema: the default sort is newest first, and size is capped at 200; the remaining parameters (search, fields, raw, limit, sort) are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List expenses'), enumerates what it covers (purchases, receipts and bills), and names the filter dimensions and result fields, which separates it in spirit from the single-item crunch_get_expense. It never names a sibling tool directly, so the differentiation is implied rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives one concrete usage instruction ('use all=true to fetch every page'), which is genuine when-to guidance for pagination. It offers no when/when-not framing against siblings such as crunch_get_expenses_total or crunch_list_recurring_expenses, so an agent must infer which listing tool fits.

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

Deploy Server

Other Tools