Skip to main content
Glama

AIApply

Apply to a job from AIApply search

apply_to_job
DestructiveIdempotent

Use this when the connected user wants AIApply to apply to a job they picked from search_jobs. AIApply adds it to their queue already approved, so it does not wait for anyone: it will be applied for and that spends a credit. This is the only point the user is asked, so call it without confirmed, show them the job, ask them, then call again with confirmed=true. Adding the same job twice is refused rather than repeated. If the account is not set up yet, it says so: call get_setup_status first. Needs an AIApply account: if the user has not signed in, calling it asks them to sign in or create one. It also needs a permission the user grants; if it was not granted, calling it asks the user to allow it. A job_id from search_jobs stays valid after either.

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": {
      "search_job_id": "<search_job_id>"
    },
    "name": "apply_to_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmedNoTrue only after the user has explicitly agreed to apply for this job.
search_job_idYesThe job_id from search_jobs. Not the job_id from list_review_jobs.

Output Schema

NameRequiredDescriptionDefault
errorNoTrue when the job could not be added.
queuedNoTrue only when the job was added.
reasonNoWhy nothing was added, when nothing was.
messageYes
user_messageNoShow this to the user rather than message.
applies_afterNoapplying_active when the job waits in the queue until applying is active on the account.
dashboard_urlNoThe AIApply dashboard, where the user manages Auto Apply.
updates_offerNoPresent once, when the account is first ready: something you may offer the user. Act on it only if they agree.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations it discloses that the application is queued already approved with no waiting, that it spends a credit, that duplicates are refused rather than repeated, and that the call surfaces sign-in and permission prompts. This is substantive context the destructiveHint/openWorldHint flags alone do not convey. It stops short of describing what the queued record looks like or what a refusal response contains, leaving that to the output 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?

Usage and the confirmation protocol are front-loaded, and every sentence carries an operational fact (cost, duplicate refusal, prerequisites). The colon-and-semicolon chaining in the middle sentences and the trailing 'stays valid after either' are slightly dense and require a re-read, which keeps it below a 5.

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 credit-spending mutation with an output schema, the description covers cost, the user-consent gate, prerequisites, duplicate behavior, and identifier provenance, so an agent can call it correctly. Minor gap: it never says what observable result distinguishes a refused duplicate from a successful apply in-session.

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 real operational meaning: 'confirmed' is not just a boolean but the pivot of a two-phase confirm-then-commit flow, and search_job_id is constrained to the search_jobs namespace and survives sign-in or permission failures.

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 first sentence states a specific verb and resource ('AIApply to apply to a job') and ties the input to a named sibling ('a job they picked from search_jobs'). The schema's note that it is not the job_id from list_review_jobs further disambiguates it from the review-queue path.

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 an explicit prerequisite route ('call get_setup_status first' if the account is not set up) and a precise two-call protocol: call without confirmed, show and ask the user, then call again with confirmed=true. It also states the duplicate case is refused, so the agent knows the boundary conditions without inference.

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