Skip to main content
Glama

Get expense

crunch_get_expense
Read-only

Retrieve a single expense with its lines, payments, attachments, credit notes and edit or delete eligibility; use raw=true to return the unchanged API object.

Instructions

Get one expense: its lines (types, VAT, amounts), payments, attachments, credit notes, and whether it can still be edited or deleted. raw=true returns the API object.

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": {
      "expense_id": "<expense_id>"
    },
    "name": "crunch_get_expense"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoReturn the API object unchanged (the base for hand-made updates)
expense_idYesExpense ID (see crunch_list_expenses)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description earns credit beyond that by disclosing the shape of what comes back (lines, payments, attachments, credit notes, computed edit/delete permission) and by explaining the raw escape hatch — meaningful context given there is no output schema. It stops short of saying what happens for a missing or unauthorized expense_id.

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 sentences, both front-loaded with the highest-value information: first what a single expense yields, then the raw-mode caveat. The parenthetical field lists are dense but each item conveys distinct return content, so nothing reads as padding.

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 read-only single-record fetch with full schema coverage and annotations carrying the safety hints, this is nearly complete: it tells the agent what fields matter and that editability/deletability is reported. The remaining gap is error/edge behavior (unknown ID, permission failure), which an agent would need to call it confidently.

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 coverage is 100%, with expense_id documented and cross-referenced to crunch_list_expenses and raw already explained as 'Return the API object unchanged (the base for hand-made updates).' The description's 'raw=true returns the API object' largely restates the schema rather than adding format or side-effect detail, so baseline 3 applies.

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?

The description uses a specific verb ('Get one expense') plus a resource and then enumerates exactly what the single record contains: lines with types/VAT/amounts, payments, attachments, credit notes, and edit/delete eligibility. That makes it clearly distinguishable from a list-style sibling such as crunch_list_expenses, which the schema itself cross-references.

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?

Usage is only implied through 'Get one expense' versus the list sibling referenced in the schema, and through the single conditional 'raw=true returns the API object.' There is no explicit when-to-use/when-not guidance, nor any statement of prerequisites such as how to obtain a valid expense_id beyond the schema's parenthetical pointer.

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