Skip to main content
Glama

Hosco Hospitality Jobs

by com.hosco

Search Jobs Tool

search-jobs-tool
Read-onlyIdempotent

Semantic + structured search over Hosco hospitality jobs. Mirrors the smart filtering and ranking from hosco-v2: hard-excludes private/expired/inactive postings, supports visibility/promotion/external filters, configurable language matching (subset/any/all), and the v2 "suggested" ordering (relevance → Hosco-native → VIP → freshness). Returns ranked matches with relevance scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityNoCity name (exact match against hosco_location.locality).
sortNoOrdering: "suggested" (default — relevance, then Hosco-native, then VIP, then freshness), "posted" (newest activation date), "update_date" (most recently updated), "title" (alphabetical).
limitNoPage size (1–50, default 10).
queryNoNatural-language search (e.g. "sommelier in Paris fine dining"). When provided, ranks by semantic similarity. When omitted, returns latest jobs filtered + sorted by the structured options.
offsetNoPagination offset (default 0).
countryNoISO-3166 alpha-2 country code, e.g. FR, GB, ES.
languagesNoCandidate language codes, e.g. ["en","fr"]. Matched against the job's mandatory fluency requirement ("Require fluency in" in hosco-v2), not the language the ad is written in. Combined with languages_mode.
departmentNoHosco category code, e.g. f-b-kitchen, housekeeping, sommelier, reception.
posted_afterNoISO date; only return jobs published on or after this date.
visibilitiesNoVisibility tiers to include: public, targeted, lite, prime (private is never returned on this public surface).
contract_typeNoOne of: internship (students only), professional (professionals only), open (both).
hide_externalNoHide jobs sourced from external aggregators (Hosco-native only).
only_externalNoOnly return jobs sourced from external aggregators.
languages_modeNoHow to interpret `languages`: "all" (job must require every code; default), "any" (job requires at least one of them), "subset" (job's required languages must all be in the provided list — i.e. the candidate speaks them all).
promotion_typesNoFilter to specific promotion statuses: 0=disabled, 1=prime, 2=lite-basic, 4=lite-full. Status 3 (private) is always excluded.
content_languageNoLanguage code the job ad itself is written in (auto-detected), e.g. "en", "fr". Use this to only show postings the candidate can actually read — unrelated to the languages filter below.
experience_years_maxNoMaximum years of experience the candidate has — only show jobs requiring less than or equal to this.

TDQS

A4/5.0
Behavior4/5

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

The description adds significant behavioral context beyond the readOnly and idempotent annotations by disclosing that private, expired, and inactive postings are hard-excluded, and by explaining the default ordering logic. This provides useful insights into how the tool behaves beyond what annotations offer.

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 two sentences, front-loaded with the core purpose, and every clause provides meaningful detail about filtering, ranking, and exclusions. There is no filler or redundant information.

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?

Given the tool's complexity (17 optional parameters, no output schema), the description covers key behaviors including exclusions, filtering, ranking, and return type. It does not specify the full return payload structure, but the detailed schema compensates, making the description sufficiently complete.

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?

The input schema already contains detailed descriptions for all 17 parameters (100% coverage). The description adds a high-level summary of filtering capabilities and the default 'suggested' ordering, but these are already captured in the schema descriptions, so the added value is marginal.

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 clearly states the tool performs semantic and structured search over Hosco hospitality jobs and returns ranked matches with relevance scores. However, it does not explicitly contrast this with sibling tools like list-jobs-tool or job-details-tool, making sibling differentiation implicit rather than explicit.

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 provides clear context for when to use the tool—for semantic or structured search with filtering and ranking—by detailing supported filters and ordering options. It does not explicitly state alternatives or exclusions, but the context is strong enough for an agent to infer appropriate usage.

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

All Hosco Hospitality Jobs 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

A4.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: list for recent jobs, search for ranked semantic matches, and details for full job information. The descriptions explicitly clarify when to use list vs search, eliminating ambiguity.

Naming Consistency4/5

All tool names follow a predictable pattern with a '-tool' suffix, but 'job-details-tool' uses a noun-noun structure while the others use verb-noun. This minor inconsistency is easy to parse and still readable.

Tool Count4/5

With only 3 tools, the set is minimal but well-scoped for a job discovery server. It covers the essential retrieval operations without unnecessary bloat, though slightly on the lower end.

Completeness4/5

The core workflow of list/search then get details is fully covered. Potential gaps like applying or filtering by specific attributes are not needed for the apparent read-only job board purpose, so no significant dead ends.

Resources