Skip to main content
Glama
benmonopoli

Greenhouse MCP

by benmonopoli
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

update_current_offer

Patch an application's current offer by setting start date, sent date, or custom fields; use application_id to target and modify the offer.

Instructions

Update the current offer on an application. Write operation.

Looks up the application's latest offer version and patches it (start date → starts_on). To find application_id: search_candidates_by_name → list_applications(candidate_id=...) → match the application to the job. For custom field IDs: list_custom_fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sent_onNoDate the offer was sent, as 'YYYY-MM-DD'
starts_atNoNew start date as 'YYYY-MM-DD'
custom_fieldsNoArray of {id, value} (or {custom_field_id, value}) — get field IDs from list_custom_fields
application_idYesGreenhouse application ID

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.5.0
    • addedInput schema / properties / application_id / description
      Added value: +"Greenhouse application ID"
    • addedInput schema / properties / custom_fields / description
      Added value: +"Array of {id, value} (or {custom_field_id, value}) — get field IDs from list_custom_fields"
    • addedInput schema / properties / sent_on
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Date the offer was sent, as 'YYYY-MM-DD'",
+  "title": "Sent On"
+}
    • addedInput schema / properties / starts_at / description
      Added value: +"New start date as 'YYYY-MM-DD'"
  2. Addedv0.3.4

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries full behavioral burden. It declares 'Write operation' and the patch-not-create semantics (operates on the latest offer version), which is genuinely useful. However it omits permission/scope requirements, what happens to fields left null or omitted, and whether changes are reversible or auditable.

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?

Purpose and write designation are front-loaded, followed by prerequisite navigation steps. Mostly economical, though the 'For custom field IDs: list_custom_fields' line repeats the schema's own note and could be dropped.

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?

An output schema exists, so return values need not be described, and the description covers the mutation target, patch semantics, and ID-discovery workflow. It falls short only on error/permission behavior, which for an unannotated write tool leaves a modest gap.

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 adds a field-name mapping ('start date → starts_on') and restates the custom-field ID source, but this largely duplicates the schema descriptions rather than adding new syntactic or validation detail.

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+resource ('Update the current offer on an application') and differentiates from read siblings like get_current_offer/get_offer. It goes further by explaining the mechanism: it looks up the application's latest offer version and patches it, so an agent knows it does not create or version offers.

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 an explicit prerequisite workflow for obtaining application_id (search_candidates_by_name → list_applications → match to job) and points to list_custom_fields for field IDs. It does not state when to prefer this over get_current_offer or other offer-related writes, so it stops short of full when/when-not guidance.

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

Deploy Server

Other Tools