searchSearch JobYap job postings by natural-language query. Matches job titles, falling back to significant keywords when the full phrase finds little. Returns result ids, titles and citable URLs for use with fetch. For structured filtering (location, company, remote, freshness) prefer search_jobs.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds meaningful behavioral details: it matches job titles and falls back to 'significant keywords' when the full phrase is low-yield. It also discloses that results include citable URLs intended for fetch. This enriches the agent's understanding of how the tool behaves without contradicting any annotations.
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?
The description is three sentences, each earning its place: the purpose, the matching behavior, and the alternative tool. It is front-loaded with the primary action and contains no filler or redundancy.
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 one parameter, a single required field, no nested objects, and an output schema plus annotations, the description covers the key aspects: what it searches, how the query works, what it returns, and when to use a sibling instead. Nothing essential is missing for a tool of this complexity.
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?
The schema provides only the type and length constraints for 'query' with 0% description coverage. The description compensates fully by explaining that the query is natural-language, matches job titles, and falls back to keywords. This gives the agent a clear model of how the parameter affects the search.
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 clearly states the tool's function: 'Search JobYap job postings by natural-language query.' It also specifies the matching strategy (job titles, fallback to keywords) and output (result ids, titles, citable URLs). It distinguishes itself from sibling search_jobs by noting the structural filtering alternative, making the purpose unambiguous.
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?
It explicitly tells when to use this tool versus the structured sibling: 'For structured filtering (location, company, remote, freshness) prefer search_jobs.' This provides a clear alternative condition, and the natural-language query description implies the intended use case. The mention of 'for use with fetch' also guides the follow-up workflow, offering actionable usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
There are two overlapping pairs: fetch vs get_job both retrieve job details, and search vs search_jobs both search listings. While the descriptions differentiate them (fetch for search result IDs, get_job for job IDs; search for natural language, search_jobs for structured filters), an agent could easily choose the wrong one without careful reading.
Tool names mix conventions: bare verb 'fetch', 'get_' prefix on three tools, 'list_' prefix, and 'search_' prefix on three others. The pattern is not uniform, though each name does convey its purpose reasonably.
Eight tools is well within the ideal range for a job search server. Each tool covers a distinct facet (search, retrieval, comments, stats, companies, locations) and none feel redundant or extraneous.
The toolkit provides a complete read-only surface for the job search domain: searching, fetching full listings, comments, company list, and location resolution. Minor gaps like per-company detail beyond job count or a direct job-by-ID endpoint could exist, but the core workflow is covered well.