Skip to main content
Glama

AICTIONBOT™ Werkbank

Search the KULIC Advisory library: articles, signal reads, practice and proof cases, execution stories, guides and method pages

search_library
Read-onlyIdempotent

KULIC Advisory library (Dario Kulic). Searches everything published on procurement, Source-to-Pay and execution: the 12 insight articles, the signal reads (9 pillar briefings, 6 signals and 15 field signals, each with the symptom, the break underneath and the next move), practice cases, anonymised proof cases, execution stories, the signal guide, role signal paths, the signal letter, industry pages, the ROI methodology, delivery principles, FAQ, offers and the Werkbank. Pages in German, English, French, Spanish, Portuguese and Chinese. Returns up to five hits with title, summary, link and the path for get_article. Keyword search without AI, no sign-in, nothing stored.

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": {
      "query": "<query>"
    },
    "name": "search_library"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of hits. Default 5.
queryYesQuestion or keywords, in the language chosen below.
languageNoLanguage of the pages searched: de, en, fr, es, pt (Brazilian Portuguese) or zh (Chinese). Default de.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / language / description
      Previous value: -"Language of the pages searched. Default de."New value: +"Language of the pages searched: de, en, fr, es, pt (Brazilian Portuguese) or zh (Chinese). Default de."
    • changedInput schema / properties / language / enum
      Previous value: -[
      -  "de",
      -  "en"
      -]New value: +[
      +  "de",
      +  "en",
      +  "fr",
      +  "es",
      +  "pt",
      +  "zh"
      +]
    • changedInput schema / properties / query / description
      Previous value: -"Question or keywords, in German or English."New value: +"Question or keywords, in the language chosen below."
    • changedInput schema / properties / query / minLength
      Previous value: -3New value: +2
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the description's job is to add beyond that, and it does: it discloses the result shape (up to five hits with title, summary, link and path), the retrieval mechanism (plain keyword search, no AI), the multilingual corpus, and that nothing is stored or requires sign-in. It stops short of describing relevance ranking or what an empty result set looks like.

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?

Purpose and return contract are front-loaded and useful, but the middle is a padded inventory ("9 pillar briefings, 6 signals and 15 field signals, each with the symptom, the break underneath and the next move") that is marketing copy rather than decision-relevant detail. The whole definition is a single long run-on sentence that could be tightened without losing selection signal.

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 three-parameter discovery tool with no output schema, the description supplies the essentials an agent needs: what corpus is covered, what the hits contain, the five-result cap, language coverage, and the handoff to get_article. Only edge-case behavior (no matches, ranking order) is missing, which is minor.

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 the schema already documents query, limit and the six-value language enum; the baseline is 3. The description reinforces the five-hit ceiling and the language set but adds no new meaning about how query text is matched or how language interacts with the indexed pages.

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?

Opens with a specific verb and resource ("Searches everything published" in the KULIC Advisory library) and enumerates the concrete corpus: articles, signal reads, practice cases, proof cases, execution stories, guides, method pages. It also distinguishes itself from the sibling get_article by explicitly returning "the path for get_article," so an agent knows this is the discovery step, not the retrieval step.

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?

The mention that hits carry "the path for get_article" implies the intended two-step flow (search, then fetch), and "Keyword search without AI" hints at what this tool is not. However, there is no explicit when-to-use or when-not-to-use statement, and no named alternative for agents that already hold a page path or want spend/analysis style answers from siblings.

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.