Skip to main content
Glama

Apply to a job listing

applyToJob
Destructive

Apply to a job for the candidate: Clera fills in the employer's form from their profile and sends it with the resume tailored to that role when generateApplicationDocuments made one, otherwise their primary resume. Run it when the candidate says to apply to this specific role. Give either jobId with position and companyName exactly as searchJobs or readJobListing (kind board) gave them (a mismatch is refused), or the applicationId of a tracked job that has a posting link (listApplications). Returns { runId } straight away; the form takes about 10-30 seconds, so call getApplicationRun with that runId next. For several listings at once use applyToJobs.

The candidate gets one confirmation before anything is sent. It only sends when every required field is filled; otherwise the run comes back needing input and nothing is sent. mode dry_run fills the form without sending, only when the candidate asks to see it first.

Workday sites (myworkdayjobs.com) need a candidate account: the run creates one with the candidate's email, or signs in to the one it made before, with a password Clera keeps. The candidate can take the account over with "Forgot your password?" there. Some Workday sites first email a "Verify your candidate account" link; getApplicationRun then reports verificationCodeRequested, and enterApplicationCode takes it.

If a run came back needing input, ask the candidate those exact questions and start again with answers. To change something getApplicationRun lists under editable, start again with that question as the answers key and the candidate's new answer. Never make up an answer. A sent application lands on their tracker as applied.

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

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": "applyToJob"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNosubmit (default) sends it after the candidate confirms; dry_run only fills the form.submit
jobIdNoThe jobId from a searchJobs result, or a readJobListing result with kind board.
answersNoReplies to questions an earlier run asked, or replacements for answers it filled in, as { <needsInput key, or the question>: <the candidate's words> }. At most 30 answers; each key and each answer up to 4,000 characters.
positionNoWith jobId: the position exactly as the result gave it.
companyNameNoWith jobId: the company name exactly as the result gave it, null when the result had none.
applicationIdNoInstead of jobId: the id of a listApplications entry that has a posting link.
confirmSubmitNoOnly when your client cannot show the confirmation prompt: "submit" once the candidate has said yes to sending this specific application, "cancel" otherwise. Never set it on your own.

Output Schema

NameRequiredDescriptionDefault
modeYes
runIdYes
positionYes
companyNameYes

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?

Well beyond the annotations, it discloses the confirmation gate ('one confirmation before anything is sent'), the all-required-fields precondition, the 10-30 second async behavior with runId polling, Workday account creation and password handling, the verification-code path via enterApplicationCode, and the privacy/usage-tracking note. The mutation is described honestly with its guards, consistent with destructiveHint=true.

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 what it does and when to run it, then groups parameters, async behavior, Workday specifics, and recovery flows into short paragraphs. It is dense but nearly every sentence carries operational information; the privacy/usage-tracking sentence is boilerplate that could be dropped.

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 a high-stakes, open-world mutation with seven parameters, the description covers the full lifecycle: invocation, confirmation, async polling, failure/needs-input recovery, editable answers, and account verification. An output schema exists, so return values need no further explanation.

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 schema already documents each field; the description adds the cross-field constraint that jobId must pair with position and companyName exactly as returned or 'a mismatch is refused', and clarifies that answers keys may be either needsInput keys or the original question text. It does not, however, restate the limits (30 answers, 4,000 chars) or the confirmSubmit escape hatch's exact wording beyond 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?

States a specific verb and resource plus the mechanics: fills the employer's form from the candidate's profile and sends it with the tailored resume when generateApplicationDocuments made one, otherwise the primary resume. It explicitly separates itself from applyToJobs for multiple listings and from getApplicationRun for polling.

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?

Gives an explicit trigger ('Run it when the candidate says to apply to this specific role'), names the alternative for batch work (applyToJobs), and specifies when to use dry_run ('only when the candidate asks to see it first'). It also explains when to re-run with answers and how to start a run with applicationId instead of jobId.

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