Search open jobs on employers' own careers sites, each confirmed open in the last 3 days.
Scored across 1 tool
With only one tool there is no possibility of misselection; its purpose (job search with filters) is unambiguous. An agent cannot confuse it with anything else on this server.
The single tool name search_jobs follows a clean verb_noun snake_case convention that reads predictably. There are no conflicting conventions to violate consistency.
A single tool is a very thin surface for a job search server; agents cannot drill into a result, inspect a full posting, or refine after a search. The one tool is well-described and earns its place, but the set as a whole is under-scoped.
The surface stops at search: there is no way to fetch a full job posting, get details for a specific listing, or retrieve employer/source metadata beyond what the two-line summary carries. This creates dead ends whenever an agent needs more than the summary and core skills.
Find open jobs by role, skill or company, with an optional place, remote, and experience level. Results come from employers' own careers sites first (confirmed open in the last 3 days); when those are fewer than asked for, jobs from Internshala and Unstop fill the rest, each marked with its source. Each result has the employer's apply link, the stated pay and minimum years when the posting gives them, a two-line summary and the core skills.
| Name | Required | Description | Default |
|---|---|---|---|
| level | No | intern, fresher (students, new graduates, up to a year), junior, mid, senior, or lead. | |
| limit | No | How many jobs, 1 to 20 (default 10). | |
| query | No | The role, skill or company, e.g. "full stack developer", "React", "data analyst", "Razorpay". It may also name a place ("in Pune") or say remote or fresher. | |
| remote | No | true for remote jobs only. | |
| country | No | A country name or its two-letter code, e.g. "IN", "US". Leave empty for every country. | |
| location | No | Where the job is, when the person names a place: a city, metro area, state or country, e.g. "Bengaluru", "Delhi NCR", "Maharashtra", "United States". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/openWorld annotations, the description discloses meaningful behavior: source priority, a 3-day freshness window for employer-site jobs, fallback aggregation with per-item source labeling, and the fields returned per result. It does not discuss rate limits or latency, but for a read-only search these are minor omissions.
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 sentences, front-loaded with the purpose, then sourcing behavior, then result contents. Dense but each sentence conveys distinct information; only the result-fields sentence could be trimmed slightly.
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 naming what each result contains (apply link, pay, minimum years, two-line summary, core skills, source label). Combined with full schema coverage and rich annotations, an agent has everything needed to call and interpret this 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 description coverage is 100%, so every parameter is already documented in the schema. The description restates that query may also encode a place or 'remote'/'fresher', but the schema's query description already says exactly that, so added value is marginal — baseline 3 applies.
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 first sentence states a specific verb (find) and resource (open jobs) plus the filter dimensions (role, skill, company, place, remote, level). An agent immediately knows this is a job search tool and what inputs shape the result set.
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 gives clear context about what the tool searches and how far it reaches (employer career sites first, then Internshala/Unstop as fallback), which tells the agent what to expect when result counts are low. There is no explicit when-not-to-use guidance, but with no sibling tools there is little ambiguity to resolve.
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.
search_jobsSearch open jobs from employers' own career sites: roles, companies and posting status.
Open jobs from 20,000+ company career sites: search, list a company's roles, read full job ads
Search jobs on verified employer job boards. Every link is the employer's own posting.
Search open jobs from company career sites by the country you can apply from, remote or onsite.
Add one secure layer between your agents and this server.