Skip to main content
Glama

Schedule or update an interview

setInterview
Destructive

Schedule, reschedule, complete or advance a candidate's interview on one of the company's roles, or move them to Offer. This is the same interview picker the Pipeline page of the dashboard uses.

Take talentId and roleId from a listPipeline candidate row, never guess them. For schedule and advance-with-date, send scheduledAt with the user's UTC offset; confirm the day, time and timezone with the user first. A scheduled date sends the candidate prep and good-luck reminders ahead of the interview. Cancel, a moved time and clear_date tell the candidate through Clera, so say that before the user confirms. When the date no longer holds and nobody has the new time yet, clear_date removes it instead of keeping the old one; never guess a time. Passing on a candidate is passCandidate, not this tool.

When the company's ATS is Ashby, the role is linked to an Ashby job and Clera added the candidate there, advance and offer also move them in the ATS, a moment later: advance to the ATS stage matching the round it opened, offer to the ATS offer stage. Forward only, never to Hired. With no matching ATS stage, or any other ATS, only Clera changes. Schedule, clear_date, complete, mark_final and cancel never move anyone in the ATS.

Clera privately records this tool's inputs and results for usage tracking and support.

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": {
      "talentId": "<talentId>",
      "roleId": "<roleId>",
      "action": "<action>"
    },
    "name": "setInterview"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgIdNoOrganization to act as. Only needed when you belong to more than one organization.
actionYesschedule: set or move the date of the current round (also reschedules to a known time). clear_date: the current round's date no longer holds and no new time is known yet; clears it so reminders queued for the old slot do not send. advance: open the next round, with a date when one is known. complete: mark the current round done. mark_final: flag the current round as the last one. cancel: cancel the current round. offer: close the current round and move the candidate to Offer.
roleIdYesThe roleId from the same listPipeline candidate row.
talentIdYesThe candidate's talentId from listPipeline.
stageNameNoName of the round to open on advance. Omit to use the role's next defined round.
completedAtNoFor complete: when the round actually ended, as an ISO 8601 datetime with offset. Omit to record now.
scheduledAtNoWhen the interview happens, as an ISO 8601 datetime with the user's UTC offset, e.g. 2026-10-02T14:00:00+02:00. Required for schedule, optional for advance. Ask the user for the time and their timezone if either is unclear; never guess.
fromTrackerUpdateNotrue when applying an update from listTrackerUpdates, copied from its setInterviewArgs.

Output Schema

NameRequiredDescriptionDefault
messageYes
outcomeYes
stageNameYes
opportunityStatusYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the destructive/openWorld annotations, it discloses real side effects: prep and good-luck reminders go to the candidate on schedule, cancel/moved time/clear_date notify the candidate through Clera, and clear_date suppresses already-queued reminders. It also details the conditional Ashby ATS propagation (advance and offer only, forward-only, never to Hired) and states the tool's inputs and results are recorded. None of this is derivable from the annotations or schema.

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?

Content is front-loaded with purpose, then preconditions, then side effects, then ATS behavior, and every paragraph carries distinct information. The ATS paragraph is dense and unbroken, so it reads longer than necessary, but no sentence is filler.

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?

For an eight-parameter mutation tool with destructive and open-world hints, it covers ID sourcing, timezone handling, candidate-visible notifications, reminder cancellation, and conditional external-system effects. An output schema exists, so return values need no explanation, and nothing an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema states only in isolation: scheduledAt belongs with schedule and advance-with-date, must carry the user's UTC offset, and requires confirming the timezone with the user first. It does not explain stageName, completedAt or fromTrackerUpdate beyond what the schema already says.

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 opening sentence names specific verbs (schedule, reschedule, complete, advance) against a specific resource (a candidate's interview on a role) and adds the Offer transition. It explicitly disclaims a sibling: 'Passing on a candidate is passCandidate, not this tool,' so an agent can distinguish it without opening schemas.

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

Usage Guidelines5/5

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

It gives concrete preconditions (take talentId and roleId from a listPipeline row, never guess them; confirm day, time and timezone with the user) and a clear when-not rule (use passCandidate to pass; use clear_date when the date no longer holds and no new time is known). The guidance is scoped to action types rather than left generic.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources