Sifter

Search open finance internships and first jobs

search_finance_internships

Read-only

Open internships and entry-level roles for students at banks, asset managers, research shops, trading firms and wealth managers, from the Sifter jobs board (updated daily). Results come in the order they close, each with the firm's own application link. Use it for questions such as "which finance internships close this week", "summer 2028 investment banking internships" or "is Evercore hiring interns". Returns a short list; the full board is at sifter.finance/jobs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_finance_internships"
  }
}

Input Schema

Name	Required	Description
`area`	No	Area of finance.
`firm`	No	A firm name, e.g. "JPMorgan", "Evercore".
`kind`	No	Internships, or full-time roles for new graduates.
`limit`	No	How many to return (default 10, at most 15).
`query`	No	Plain words, e.g. "equity research intern NYC" or "investment banking for sophomores". Matched against the firm, role, area and location. Years, "this week" and class standing (sophomore, junior) are understood.
`summer`	No	The summer an internship is for, as a year, e.g. "2028".
`location`	No	A city or state, e.g. "New York", "Chicago", "TX".
`class_year`	No	Graduation year the firm asked for, e.g. "2029".
`closing_within_days`	No	Only roles whose application closes within this many days.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add context. It does: results are ordered by closing date, each carries the firm's own application link, the response is deliberately a short list, and the underlying board refreshes daily. It omits what happens when no roles match and whether multiple filters are combined as AND, so it stops short of full behavioral disclosure.

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?

Front-loaded with the capability and coverage, then examples, then return behavior and the escape hatch to the full board. It is a single dense paragraph with little waste, though the example questions partially duplicate what the query parameter already illustrates and the trailing URL is minor padding.

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?

With 9 optional parameters and no output schema, the description carries the return-value burden and does so by describing ordering, per-result application links, and result-count expectations. Gaps remain around empty-result behavior and filter combination semantics, which matter for a nine-filter search tool.

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%, so every parameter including the two enums already carries its own explanation, and the description's phrasing ('summer 2028 investment banking internships', 'close this week') largely restates what the schema says about summer, query and closing_within_days. It adds no new syntax, defaults, or interaction rules beyond the schema, 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?

States a specific verb and resource (open internships and entry-level roles), names the covered firm types (banks, asset managers, research shops, trading firms, wealth managers) and the data source (Sifter jobs board, updated daily). An agent can immediately tell this is a finance-jobs search and not the textbook-reading siblings.

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?

Gives concrete example questions that map directly onto the tool's capability (closing this week, summer 2028 IB internships, firm-specific hiring), which effectively tells the agent when to reach for it. It does not state when NOT to use it or point to the sibling finance_internships_overview for broader/aggregate needs, so guidance is clear but not complete.

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

All Sifter tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?