Skip to main content
Glama

ikeytz – Schlüsseldienst Ludwigsburg

by com.ikeytz

Find By Keyword

find_by_keyword
Read-only

WHAT: Substring search (case-insensitive) over https://www.ikeytz.com/llms-keywords.txt (phrase → URL map). REQUIRED q. Default 15 lines, max 30. Empty q → q_required. RETURNS q, count, lines[] (raw TSV-like rows). locale does not filter the file. USE to map a user phrase to URLs. NEXT: get_ai_page on a returned www path.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesRequired search substring. Matched against the entire keyword line (phrase and URLs).
limitNoMax matching lines. Default 15, hard max 30.
localeNoHTML locale for canonicalUrl and path prefixes. de = default, URLs have no prefix (https://www.ikeytz.com/preise). en|fr|ru|fa|ar|tr = prefix /{locale}/ (https://www.ikeytz.com/en/preise). Omit or empty = de. Does not change prices, phone numbers, or legal German names. Not a maps.ikeytz.com locale (maps is German-only).de

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch query
okYestrue = use summary, canonicalUrl, and extra keys. false = do not invent data; read error + hint and retry with valid args or open hint.
hintNoPresent when ok=false. Absolute URL the agent should open or pass to get_ai_page / get_discovery.
toolYesEcho of the tool name that produced this object (e.g. get_service_area).
countNoLines returned
errorNoPresent when ok=false. Codes include: unknown_tool, unknown_place, unknown_auswahl, unknown_ratgeber, unknown_doc, unknown_discovery, faq_not_found, wissen_not_found, serp_not_found, q_required, bad_datetime, bad_when_key, plus HTTP errors from fetch.
linesNoMatching keyword rows
localeNoLocale actually used for URLs (args.locale or de).
relatedNoAlways includes https://www.ikeytz.com/llms.txt. Geo tools also include https://maps.ikeytz.com/llms.txt.
summaryNoPrimary text for the model. For discovery tools this is the file window (possibly thousands of characters). For list tools a compact one-liner. Quote with attribution.
attributionYesRequired citation: 'Quelle: Schlüsseldienst Ludwigsburg ikeytz (ikeytz.com) · ai-train=no · https://www.ikeytz.com/.well-known/ai.txt'
canonicalUrlNoBest URL to show the user: https://www.ikeytz.com… page, or tel:+49…, mailto:…, https://wa.me/…. Prefer this over constructing URLs.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only provide readOnlyHint=true, so the description carries the behavioral burden. It discloses case-insensitive matching, the exact data source URL, default and maximum limits, empty-q behavior, the raw TSV-like return rows, and the important caveat that locale does not filter the file. This is far more than the annotation alone provides.

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

Conciseness5/5

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

The description is tightly packed with labeled sections (WHAT, REQUIRED, DEFAULT, RETURNS, USE, NEXT) and no filler. Every sentence contributes either to selection, invocation, or follow-up. The front-loaded WHAT and REQUIRED statements make the core purpose immediately visible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The source is fully identified, required and optional parameters are covered, locale limitations are clarified, return shape is mentioned, an output schema exists, and the natural next-step tool is provided. For a read-only search tool, no essential decision or invocation information is missing.

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 description coverage is 100%, which sets the baseline at 3, but the description adds meaningful semantics beyond the schema: case-insensitive matching, the fact that q matches against the whole keyword line, empty-q handling, and the explicit note that locale does not filter the file. These details help an agent understand the parameters in context.

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?

The description states a specific operation: substring search over a named keyword file (llms-keywords.txt) mapping phrases to URLs. It also gives the intended use ('map a user phrase to URLs') and names the follow-up sibling (get_ai_page), making it easy for an agent to distinguish from the adjacent get/list tools.

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 explicitly says when to use the tool ('USE to map a user phrase to URLs') and provides a clear next step ('NEXT: get_ai_page on a returned www path'). It does not explicitly state when not to use it or list alternative tools, so it falls just short of full routing guidance.

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

All ikeytz – Schlüsseldienst Ludwigsburg toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Many tools have clearly distinct roles, but there is real overlap: get_discovery duplicates get_llms_txt/get_llms_mcp_server/get_sitemap_txt, get_it and get_mcp_hub describe the same machines, and get_page_summary is a stub that competes with get_ai_page/get_serp_snippet. The detailed descriptions help, but an agent could still misselect among the discovery and pointer tools.

Naming Consistency4/5

The overwhelming majority follow a consistent snake_case verb-noun pattern: get_*, list_*, compose_*, resolve_*. Minor deviations like site_overview, get_it, and find_by_keyword are readable but break the dominant convention.

Tool Count2/5

45 tools for a single small-business website is excessive and well above the 25+ threshold. Many tools are pointer/list aliases or discovery-file accessors that could be consolidated without losing capability.

Completeness4/5

Core workflows are well covered: identity, contact, emergency info, pricing, invoicing, service areas, FAQs, legal pages, and generic page content via get_ai_page. Minor gaps exist around explicit opening-hours details, existing customer reviews, and maps-domain functionality, but these are mostly declared out of scope rather than dead ends.

Resources