Skip to main content
Glama

AICTIONBOT™ Werkbank

Buying policy in five questions: value limits, number of quotes, specification, award note, contract and approval, plus a check of orders against the rules

write_buying_policy
Read-onlyIdempotent

AICTIONBOT™ buying policy by KULIC Advisory (tool 39), built on the Execution Toolkit templates T32 (operating model) and T03 (process taxonomy with RASCI). Writes a one-page buying policy for a business without a procurement department from three value limits (direct order up to small_limit, three quotes from quote_limit, managing-director approval from board_limit; defaults 1,000, 10,000 and 25,000 euros) and the name of the approver. Optionally answers the five questions for one purchase (purchase_value, purchase_type goods, service, capital purchase, software or consulting, preferred_supplier with framework agreement yes or no): how many quotes, specification, award note, contract, who approves. Optionally checks a list of orders (order, supplier, value, type, framework, quotes, specification, award note, contract, approval) against the rules, with red and yellow findings and possible order splitting. Deterministic, no AI, nothing stored. Not legal advice. Needs sign-in: runs with an AICTIONBOT™ Werkbank licence; without a licence one check per connection every 30 days is free (sign in with “Connect without a licence”).

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": "write_buying_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
ordersNoOptional order rows: order, supplier, value, type, framework (yes/no), quotes (number), specification, award_note, contract (yes/no), approval (who approved). German column names work too.
companyNoCompany name for the policy title.
approverNoWho approves above board_limit. Default managing director.
languageNoLanguage of the answer. Default de.
board_limitNoApproval by the managing director from this value in euros. Default 25000.
quote_limitNoThree quotes from this value in euros. Default 10000.
small_limitNoOrder directly up to this value in euros. Default 1000.
purchase_typeNoType of the purchase: goods, service, capital purchase, software, consulting (German words work too).
purchase_valueNoOne purchase to check: total value in euros over the whole term.
preferred_supplierNoIs there a preferred supplier with a framework agreement?

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the description is not obligated to re-explain safety. It still adds real value beyond them: deterministic and no AI, 'nothing stored' (clarifying that 'Writes' means generate, not persist, which pre-empts an apparent conflict with readOnlyHint), 'Not legal advice', and concrete licensing/auth constraints including the 30-day free check without a licence.

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

Conciseness2/5

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

The opening is buried under branding and template citations ('AICTIONBOT™ ... (tool 39), built on the Execution Toolkit templates T32 ... T03') before the actual verb appears, and the description is a single sprawling sentence-chain with long parenthetical enumerations. Much of the content is functional, but the promotional and template-reference material does not earn its place.

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 10-parameter tool with no output schema, the description covers what is produced (a one-page policy, red/yellow findings, possible order splitting), the rule defaults, and access prerequisites. The main gap is the shape of the returned findings, but the annotations plus this text give an agent enough to call it correctly.

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 ten parameters are already documented, and the description mostly restates them (limits, defaults, purchase_type values, preferred_supplier). The one added semantic is the relationship between the three limits – direct order up to small_limit, quotes from quote_limit, approval from board_limit – which helps an agent set them coherently, but that is largely visible in the schema defaults too.

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 states a concrete verb and artifact: 'Writes a one-page buying policy' from three value limits plus an approver, with optional per-purchase Q&A and optional order auditing. The three-in-one scope is spelled out, so an agent knows exactly what the tool produces, though no sibling tool is named to differentiate it from checks like check_approval_matrix.

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 the repeated 'Optionally answers...' and 'Optionally checks...' clauses, which tell the agent that populating purchase_value or orders activates extra behaviors. There is no explicit statement of when to prefer this over sibling tools or when it is the wrong choice, leaving routing to inference.

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.