Skip to main content
Glama

Run a purchasing report

purchasing_report
Read-onlyIdempotent

aged_payables: what is owed to each supplier on as_of (default today), by how long past due: current (not due yet), 1-30, 31-60, 61-90 and over 90 days, per currency. spend: what each supplier billed from-to (by issue date; default this month) and what was paid to them in it. To show a person, put it in a view (view_show). Free.

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": {
      "report": "<report>"
    },
    "name": "purchasing_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoYYYY-MM-DD
fromNoYYYY-MM-DD
as_ofNoYYYY-MM-DD
reportYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds default behavior beyond them: as_of defaults to today, from-to defaults to this month, and spend is dated by issue date. It also adds a cost trait ('Free') not present in structured fields. No output shape, sorting or limit info, but no output schema exists to lean on either.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and free of filler, but it is telegraphic and not front-loaded — there is no opening sentence stating what the tool is, and the reader has to parse two colon-led clauses before knowing the subject. Every sentence earns its place, but the structure makes the first read harder than necessary.

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?

Both report modes, their date semantics, their defaults, and the follow-on step for presenting results are all covered, which is enough to call this correctly. Gaps are minor: which parameters are ignored per report mode, and per-currency grouping behavior is mentioned but not explained.

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 75% and the schema entries for to/from/as_of only say 'YYYY-MM-DD', so the description carries real weight: it defines as_of as the aging cutoff and from-to as the issue-date billing window, which is a per-report semantic the schema does not encode. It could go further by stating explicitly that as_of applies only to aged_payables and from/to only to spend.

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 two report modes are spelled out precisely: what is owed per supplier by aging bucket, and what was billed vs paid per supplier. An agent can tell what the tool computes. It lacks a leading one-line statement of purpose (the description opens mid-label with 'aged_payables:'), but the substance is specific and distinguishes it from siblings like purchasing_list_bills.

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?

The two enum values are each described with the condition that selects them, and the description routes presentation to a sibling: 'To show a person, put it in a view (view_show).' No explicit when-not guidance or mention of related reporting siblings such as invoices_report or books_report, so it stops short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources