Skip to main content
Glama

AICTIONBOT™ Werkbank

Sourcing plan for a category: field, approach (tender, partnership, secure supply, simplify), levers, negotiation style and a dated timeline to the contract

plan_sourcing
Read-onlyIdempotent

AICTIONBOT™ sourcing plan by KULIC Advisory, built on the Execution Toolkit template T08 (sourcing strategy). From category, annual spend, number of suppliers, share of the top three, market competition, substitution risk, switching cost, strategic importance, demand variability, how standard the specification is, contract end and notice period it derives the field (strategic, leverage, bottleneck, transactional), the approach (tender, collaborative negotiation with a second source, secure supply, or simplify), the levers with their impact, the negotiation style and a phase plan with dates. With a contract end and notice period it works back to the latest decision date and warns when the time is too short. Names the inputs that would make the plan more precise. Deterministic, no AI, nothing stored. 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

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": {
      "category": "<category>"
    },
    "name": "plan_sourcing"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNo
noticeNoNotice period, e.g. '3 months' or '6 weeks'.
categoryYes
languageNoLanguage of the answer. Default de.
suppliersNoNumber of current suppliers.
start_dateNoPlanned start. Default: as late as the contract end allows, at the earliest today.
top3_shareNoShare of spend with the three largest suppliers, percent.
annual_spendNoAnnual spend in euros.
contract_endNoYYYY-MM-DD.
specificationNostandard or custom.
switching_costNohigh, medium or low.
substitution_riskNohigh, medium or low.
demand_variabilityNohigh, medium or low.
market_competitionNohigh, medium or low (or 1 to 5).
strategic_importanceNohigh, medium or low.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare that this is a read-only, idempotent, non-destructive, closed-world operation. Beyond that structured safety profile, the description adds the useful facts that the tool is deterministic and stores nothing, and that it warns when the contract end plus the notice period leave too little time to work back to the latest decision date. The licence and sign-in details add further context. It omits the response shape, but no output schema exists, so some burden remains. A score of 3 fits given the annotation coverage.

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?

The content is dense but well front-loaded: the derived outputs (field, approach, levers, negotiation style, phase plan) come before the licensing note. Branding and template references ('AICTIONBOT™', 'KULIC Advisory', 'Execution Toolkit template T08') are filler that an agent does not need. A single run-on sentence carries all the content.

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 15-parameter analytic tool with no output schema, the description adequately conveys what is produced and the free-trial constraint. The input relationship that matters most, namely contract_end plus notice, is explained. The derived output categories are described well enough for an agent to know what to expect.

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 87%, so the schema already documents most parameters, including the allowed values for notice, start_date, contract_end, and the high/medium/low fields. The description mostly enumerates the same inputs rather than adding new semantics. Its one real contribution is explaining that contract_end and notice drive a backwards calculation to the latest decision date. Under the given schema coverage, baseline 3 is appropriate and is only marginally exceeded.

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 gives a specific verb-and-resource: it derives a sourcing plan (Kraljic field, approach, levers, negotiation style, dated phase plan) from a set of category inputs. It is possible to tell it apart from plan_negotiation and build_category_profile because the deliverables it names are distinct. However, it does not explicitly name a sibling or state which tool to use instead, so it stays below 5.

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 description makes the context of use clear: you call it once you have the category characteristics (spend, supplier concentration, competition, switching cost, contract end, notice period). The sentence 'Names the inputs that would make the plan more precise' implies iterative follow-up calls, but there are no explicit when-not-to-use conditions and no direct comparison with alternatives.

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.