Physiotherapy, occupational and speech therapy jobs in Germany, with one-minute application links.
Scored across 2 tools
search_jobs and get_job target clearly different operations: discovery via filters versus retrieval of a single posting by slug. The descriptions explicitly state the relationship (get_job uses the slug from search_jobs), leaving no realistic chance of misselection.
Both names follow the same verb_noun snake_case pattern (search_jobs, get_job) and use the same domain noun consistently. Resource pluralization is idiomatic (plural for collection search, singular for single-item fetch).
Two tools is thin on paper, but this is a read-only job board where search plus detail retrieval is the natural minimal pair. Each tool earns its place with no redundant surface, though a small amount of headroom exists for pagination or filter-discovery tools.
The core lifecycle for a job-seeker flow (find postings, then open a full JobPosting with application link) is fully covered. Minor gaps: no tool to enumerate valid filter values (regions, employment types) or to handle result pagination, so agents may have to guess parameter vocabularies.
One position with its full schema.org JobPosting (description, location, employment type, employer) and the application link. Use slug from search_jobs.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral context by specifying the return payload (a complete schema.org JobPosting plus the application link), which matters since no output schema exists; it does not mention failure behavior for a missing slug.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with zero filler: the return content is front-loaded and the argument source follows. Nothing repeats the tool name or the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter read tool with annotations covering safety and no output schema, the description supplies both the return shape and the argument provenance. Only the error case for an invalid or unknown slug is left unaddressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the schema types slug as a bare string, so the description must carry the load. It usefully states that the slug comes from search_jobs, but adds nothing about format, case sensitivity, or validity beyond that origin.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"One position with its full schema.org JobPosting" identifies a single-resource fetch and enumerates the returned fields (description, location, employment type, employer, application link). It is clearly distinguishable from the sibling search_jobs, though the retrieval verb is implied rather than stated outright.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Use slug from search_jobs" gives explicit context: this is the drill-down step after a search, and the slug argument originates there. It stops short of stating exclusions or what happens when the slug is unknown, so it sits just below a full when/when-not statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search open positions for physiotherapists, occupational therapists and speech and language therapists in Germany. All filters are optional and combined with AND. Returns title, employer, city, postal code, region, employment type and the links to the job page and the application (about one minute, no CV).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | Words from the job title, employer or profession, German or English, e.g. 'Physiotherapeut Neurologie' or 'speech therapist' | |
| location | No | City name or the first digits of a German postal code, e.g. 'Köln' or '50' | |
| profession | No | physiotherapeut = physiotherapist, ergotherapeut = occupational therapist, logopaede = speech and language therapist | |
| employment_type | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this as a read-only, closed-world lookup, and the description usefully adds that it takes about a minute and requires no CV, which sets agent expectations. It also enumerates the returned fields, though it says nothing about result ordering 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three dense sentences, front-loaded with the domain scope, then the filter semantics, then the return shape. No filler or repetition of the title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by listing the returned fields and linking behavior, which is what an agent needs to decide whether to call it. The remaining gap is pagination/limit behavior, minor for a small five-parameter search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 60%: query, location and profession are already documented in the schema, and employment_type and limit are not. The description's contribution is the AND-combination rule, which is genuinely beyond the schema, but it does not explain the limit parameter's interaction with total matches.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ('Search open positions') and scopes it to three therapy professions in Germany, so an agent immediately knows the domain. It does not explicitly contrast itself with the sibling get_job, though the verb 'search' versus 'get' makes the split inferable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'All filters are optional and combined with AND' tells the agent how to compose the inputs, and the profession list clarifies what can be searched. It stops short of stating when to prefer get_job for a single known posting or what to do with zero results.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_jobsearch_jobsOpen physiotherapy jobs in Germany from practice careers pages, with 60-second apply links.
Jobs in Germany, Austria and Switzerland matched to your resume.
Jobs, salaries, net pay and labour-market data for Germany from the JobJump job board.
Jobs from 10,000+ company career sites, Germany's Arbeitsagentur, Wellfound startups; EU suppliers.
Add one secure layer between your agents and this server.