Greenhouse MCP

stale_applications

Find applications with no activity for N days, sorted by stalest, to review untouched candidates and clean up pipelines with bulk rejection.

Instructions

Applications with no activity for N days, sorted by stalest. Read-only.

Users say "who's been sitting untouched?" Use the results with bulk_reject for pipeline cleanup. Pass job_id (list_jobs → match by name) to filter to one job. Each row includes the current stage and job name.

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": "stale_applications"
  }
}

Input Schema

Name	Required	Description
`days`	No	Minimum days without activity
`limit`	No	Max applications to return
`job_id`	No	Filter to one job — list_jobs → match by name

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.5.0Oct 5, 2026
- addedInput schema / properties / days / description
```
Added value: +"Minimum days without activity"
```
- addedInput schema / properties / job_id / description
```
Added value: +"Filter to one job — list_jobs → match by name"
```
- addedInput schema / properties / limit / description
```
Added value: +"Max applications to return"
```
Addedv0.3.4Apr 15, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations present, the description carries the full behavioral burden, and it does declare "Read-only" plus the sort order — genuinely useful for a mutation-free query tool. It omits pagination behavior, what counts as "activity," permission requirements, and default values (14 days / 50 rows), leaving real gaps.

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-loads the core definition and the read-only note in the first two short sentences, then adds workflow context. Every sentence contributes, though the "Each row includes the current stage and job name" line is largely redundant with the existing output schema.

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?

For a parameterized read-only list tool with 100% schema coverage and an output schema, the description supplies the missing behavioral layer (read-only, sort order, workflow chaining). It falls short only on pagination and the definition of inactivity, which an agent might need before tuning days.

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 all three parameters (days, limit, job_id) are already documented in the schema, including the list_jobs lookup hint for job_id. The description adds only the staleness-sorting concept and reuses the same job_id guidance, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (applications), a precise filter (no activity for N days), and an ordering guarantee (sorted by stalest), which is far beyond a restatement of the name. It does not explicitly name or contrast with the nearest siblings (candidates_needing_action, pipeline_summary, search_pipeline_candidates), so it stops short of full sibling differentiation.

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 a concrete workflow cue ("Use the results with bulk_reject for pipeline cleanup") and a chaining instruction (list_jobs → match by name → pass job_id). It does not state when NOT to use it or name a competing tool, but the context for use is unambiguous.

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

Deploy Server