Conecto

Change a job

hiring_update_job

Change a job's details, or open and close it (a closed job stays readable but takes no applications). Give only what changes. Costs $0.01 per call; nothing if it fails.

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": {
      "job": "<job>"
    },
    "name": "hiring_update_job"
  }
}

Input Schema

Name	Required	Description
`job`	Yes	The job (its slug from hiring_list_jobs).
`title`	No	e.g. "Bike mechanic".
`filter`	No	Who the hiring team hears about: {"min_match": 70, "required": true, "max_risk": "minor"} (the lowest match score, every required criterion shown, the most risk the checks may find). With a filter, the team is told about a candidate once your screening (hiring_record_screening) passes it, in your words: by email to the careers page's notify address and as the event hiring.candidate_passed; not about every application as it arrives. null: no filter.
`salary`	No	{"min": 52000, "max": 60000, "currency": "USD", "period": "year"} (period: hour, month or year).
`stages`	No	The steps between Applied and Hired/Rejected; default Screen, Interview, Offer.
`status`	No
`criteria`	No	What a screening checks: [{"text": "Three years in customer support", "required": true, "weight": 3}]. weight, 1 to 5, is how much it counts in the match score; a required one a screening does not find is named. Give a criterion's id (from hiring_list_jobs) when rewording it, so past screenings stay attached. Used by hiring_screen_queue and hiring_record_screening.
`location`	No	Where the job is: the city with its state or country, e.g. "Portland, OR" or "Berlin, Germany"; for a remote job, the countries people may work from, e.g. "Remote (US, Canada)". Google's job search lists an open job once its location names the country.
`questions`	No	Extra questions on the application form: [{"label", "type", "required", "help"}]. type: short_text, long_text, yes_no, choice, multi_choice (both with "options": ["...", "..."]), number, date or url. A yes_no question can set "required_answer": true or false; any other answer flags the applicant (never an automatic no). A date question can take include_time (a time too), range (a first and a last day), and earliest and latest ("2026-11-01", or "today", "today+7", "today-30").
`workplace`	No
`department`	No
`description`	No	Markdown: the role, what they will do, what you look for, what you offer.
`employment_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedInput schema / properties / location / description

Previous value: -"e.g. \"Portland, OR\"."New value: +"Where the job is: the city with its state or country, e.g. \"Portland, OR\" or \"Berlin, Germany\"; for a remote job, the countries people may work from, e.g. \"Remote (US, Canada)\". Google's job search lists an open job once its location names the country."

First observedOct 28, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Adds real value beyond the annotations: per-call pricing ($0.01), the no-charge-on-failure rule, and the precise meaning of closing a job (readable but accepting no applications). It does not say what permissions are needed or whether changing stages/criteria affects in-flight applicants, which matters for a 13-param mutation with destructiveHint=false.

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?

Three short sentences, front-loaded with what the tool does, then the state semantics, then the delta rule and cost. Every sentence earns its place; only the cost sentence is arguably secondary context.

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

Completeness3/5

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

For a 13-parameter mutation with nested objects and no output schema, the description covers cost and the close-state effect but is silent on permissions, whether omitted fields are preserved versus reset, and consequences for existing screenings. Adequate but with clear gaps given the tool's complexity.

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 coverage is 69% and the nested filter, criteria, questions and salary objects are documented in the schema itself. The description contributes only the partial-update rule; it says nothing about rewording criteria ids, stage list replacement, or how filter interacts with hiring_record_screening, all of which would have added meaning.

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 verb and resource ("Change a job's details") and adds the open/close lifecycle operation that an agent could not infer from the name. It implicitly separates itself from hiring_create_job by requiring a job and only changed fields, though it never names that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Give only what changes" is useful partial-update guidance, and the closed-state explanation hints at when to set status. But there is no explicit routing such as "use hiring_create_job to create a job" or "use hiring_design_careers for the careers page copy", leaving alternatives implicit.

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

All Conecto 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?