Skip to main content
Glama

Market and Regulatory Data Feeds — Zinin M2M Hub

XING Jobs (DACH) Scraper

xing-jobs
Read-only

Walk xing.com's own job sitemap and pull public job listings from Germany/Austria/Switzerland: title, company, location, employment type, posted date, industry, and (optionally) the full description — straight from each job's own public page. — $0.02/call, x402 (USDC on base).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
max_itemsNoHow many job rows to deliver, at most. This Actor walks xing.com's own job sitemap and visits each candidate job page individually — a meaningful share of freshly-listed jobs are already withdrawn (HTTP 410) by the time they're visited, which is normal churn, not a fault. Extra candidates are attempted automatically to compensate, so this number is a target, not a guarantee.
freshness_daysNoSkip sitemap entries older than this many days. In practice xing.com's own sitemap entries are typically only minutes to hours old at any given time, so this rarely filters anything out.
keyword_filterNoOptional case-insensitive substring match against each job's title, applied on this Actor's side after fetching the job's own page. xing.com's job search itself needs a browser session and is not used here — there is no server-side keyword search on this Actor. Leave empty to keep every job found.
sitemap_override_urlNoAdvanced: override the internal xing.com jobs sitemap URL this Actor walks. Leave empty to use the live xing.com jobs sitemap index. Mainly useful for diagnostics.
fetch_full_descriptionNoInclude the job's full description text in the output row. This Actor already fetches each job's own page to get any data at all (title, company, location...), so the description costs no extra request either way — this setting only controls whether it's kept in the row.

TDQS

A4.3/5.0
Behavior5/5

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

Annotation already sets readOnlyHint=true and destructiveHint=false, but the description adds valuable behavioral detail: the high churn rate of withdrawn jobs (HTTP 410), automatic compensation attempts, the fact that fetching full descriptions costs no extra request, and the lack of server-side keyword search. This goes well beyond the annotations.

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 description is two sentences, front-loaded with the primary purpose and output fields, then adds behavioral context. The cost note ('$0.02/call, x402 (USDC on base)') is tangential to tool selection and invocation, preventing a perfect 5.

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 tool with 5 optional parameters and no output schema, the description covers the core behavior, source, output fields, and important caveats (410 churn, compensation, no server-side search). It lacks a precise return-structure description, which would be needed with no output schema, so it is not a 5.

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% with rich explanations for all 5 parameters (e.g., max_items explains the 410 churn, keyword_filter explains client-side filtering). The tool description itself adds no parameter-level detail beyond what the schema already provides, so the baseline 3 applies.

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 verb ('Walk xing.com's own job sitemap and pull...') with a clear resource (public job listings from DACH) and lists the output fields. It inherently differentiates from sibling job scrapers by naming XING and the DACH region.

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 gives clear context: it scrapes XING's public sitemap for DACH jobs and explicitly notes that XING's own job search is not used (requires a browser session). However, it does not explicitly name alternative tools or provide when-not-to-use guidance, so it falls just 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.

TDQS

B3.4/5.0
Disambiguation2/5

Many tools have overlapping purposes, with over a dozen real-estate scrapers and half a dozen job boards differentiated only by geography. While descriptions are clear, an agent would struggle to pick the correct tool without prior knowledge of the specific site or region, leading to frequent misselection.

Naming Consistency2/5

Tool names use a mix of lowercase-hyphenated (boss-az, clinical-trials-monitor), underscore (pricing_info), and long descriptive phrases (official-gazette-regulatory-action-router). No consistent verb_noun pattern exists; some start with source domains, others with action nouns. This lack of predictability makes navigation confusing.

Tool Count3/5

36 tools is on the heavy side for a server that could have been more focused. While a 'data hub' can justify many endpoints, the high number of near-identical scrapers (12+ real estate, 6+ job boards) suggests bloat rather than well-scoped functionality. A leaner set with parameterized regional filters would be more appropriate.

Completeness2/5

The claimed domain 'Market and Regulatory Data Feeds' is poorly served: there are no stock/forex/commodity price feeds, few global regulatory sources (only FDA, SEC, EU tenders), and many tools are for job and property listings which are tangential. The set feels like a random aggregation rather than a coherent surface, with obvious gaps for core market and regulatory data.

Resources