open-greenhouse-mcp

fetch_new_applications

Retrieve job applications submitted since a specified ISO date, grouped by job, to review new candidates, sources, stages, and screening answers. Optionally filter to a single job or status for targeted follow-up.

Instructions

Applications since a date, grouped by job — the daily digest. Read-only.

Users say "what new applications came in since yesterday?" Pass since as an ISO date. Optionally filter to one job with job_id (list_jobs → match by name). Returns applications grouped by job with candidate names, sources, stages, and screening answers.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since": "<since>"
    },
    "name": "fetch_new_applications"
  }
}

Input Schema

Name	Required	Description	Default
`since`	Yes	ISO 8601 date — e.g. '2026-04-14' for yesterday
`job_id`	No	Filter to one job — list_jobs → match by name
`status`	No	Filter by status: 'active', 'rejected', or 'hired'	active
`include_candidate_details`	No	Include candidate names (adds API calls)

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.0Aug 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden. It states 'Read-only,' which is a key behavioral trait, and describes the return format (grouped by job with candidate names, sources, stages, screening answers). It does not mention potential side effects or API cost details beyond the schema, but the read-only declaration and output shape provide solid transparency.

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?

Three sentences: a front-loaded summary, a user-quote example, and a return-format explanation. Every sentence earns its place, with zero fluff. The structure is clear and immediately scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and the read-only nature, the description covers the essentials: purpose, usage example, parameter handling, and return shape. It adequately differentiates from sibling tools and provides enough context for an agent to select and invoke it correctly.

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 the baseline is 3. The description repeats the schema guidance for 'since' and 'job_id' (e.g., 'list_jobs → match by name') but adds no new parameter semantics beyond what the schema already provides. It does not mention 'status' or 'include_candidate_details' defaults, relying on the schema.

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?

The description uses a specific verb+resource+scope: 'Applications since a date, grouped by job — the daily digest.' It clearly distinguishes from siblings like list_applications by emphasizing grouping and the daily digest use case, and it explicitly mentions returning candidate names, sources, stages, and screening answers.

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 a clear use case: 'Users say "what new applications came in since yesterday?"' and explains how to filter by job via list_jobs. It does not explicitly name alternatives or state when not to use it, but the context makes the primary scenario obvious. It lacks direct exclusions, so it falls short of a 5.

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