Skip to main content
Glama
aweher

invoiceninja-mcp

by aweher

invoiceninja_list_expenses

Read-onlyIdempotent

List expenses from Invoice Ninja with filters for client, status, date range, and tags. Sort and paginate results to find and review expense records.

Instructions

List expenses from Invoice Ninja with filtering, sorting and pagination. client_status values: all, logged, pending, invoiced, uninvoiced, paid, unpaid, uncategorized. extra_filters keys: number, amount, categories (category ids, comma separated), vendor_ids, project_ids, payment_type, has_invoices, date_range ('YYYY-MM-DD,YYYY-MM-DD'); created_between / updated_between ('YYYY-MM-DD,YYYY-MM-DD'), tag_ids (comma separated), assigned_user_ids. Related names are resolved automatically (client_name, vendor_name). Use invoiceninja_get_expense with an id from this list for the full record.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, starting at 1
sortNoSort as 'column|asc' or 'column|desc', e.g. 'date|desc'
fieldsNoJSON format only: return just these top-level fields (id is always included), e.g. ['number', 'client_name', 'balance', 'due_date']
filterNoFree-text search across the main columns (number, name, contacts, notes…)
statusNoLifecycle filter, comma separated: active, archived, deleted (e.g. 'active' to skip archived and deleted records)
includeNoExtra relations to embed, comma separated (e.g. 'payments,activities')
per_pageNoRecords per page (1-100)
client_idNoOnly records of this client (hashed id)
client_statusNoBusiness status filter, comma separated; one or more of: all, logged, pending, invoiced, uninvoiced, paid, unpaid, uncategorized
extra_filtersNoAdditional API query filters as name -> value (see the tool description)
response_formatNo'markdown' (default) for a readable summary, 'json' for complete machine-readable data (empty fields removed)markdown

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safe-read profile is fully covered without the description. The description does add one genuine behavioral detail — that related names like client_name and vendor_name are auto-resolved — but it says nothing about pagination behavior or result volume.

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 is front-loaded, then the enum values, then the filter-key reference, then the routing note — a logical order. The extra_filters line is dense but every token is load-bearing. No filler sentences.

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 an 11-parameter list tool with no output schema and annotations covering the safety profile, the description supplies the filter vocabulary, the auto-resolution behavior, and the hand-off path to the detail tool. Nothing critical is missing, though return-shape expectations (markdown vs json) are left to the schema.

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, but the description earns more by enumerating extra_filters keys (number, amount, categories, vendor_ids, project_ids, payment_type, has_invoices, date_range, tag_ids, assigned_user_ids) that the schema only alludes to with 'see the tool description.' It also supplies the date-range format 'YYYY-MM-DD,YYYY-MM-DD' and notes comma-separated semantics.

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?

The description opens with a specific verb+resource+scope: 'List expenses from Invoice Ninja with filtering, sorting and pagination.' The resource name distinguishes it from the many sibling list_* tools, and it names invoiceninja_get_expense as the follow-up for full records. It stops short of explicitly contrasting with the closest sibling, invoiceninja_list_recurring_expenses.

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 explicitly routes the agent: 'Use invoiceninja_get_expense with an id from this list for the full record,' which clearly separates the list and detail tools. However, it offers no when-not-to-use guidance or prerequisites for calling the list endpoint.

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