Skip to main content
Glama

AceRound AI Interview Copilot

stop_job_apply_task

Stop what the apply AI is doing, the same as the user pressing Stop in the app: with taskId, only that conversation stops (in one-click apply that application also leaves this run); without it, the same as "Stop all" on the application list (running ones stop now, queued ones are not applied to) plus every other running conversation. Filled pages stay as they are; send_job_apply_instruction can have it continue later. Replies with the state read back after stopping. Requires the AceRound Auto Apply desktop app on the user’s computer to be signed in and open (running in the background after closing the window also works); if the app is offline or outdated, the tool says so. (Requires the user's sign-in with scope job_applications:write.)

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": "stop_job_apply_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdNoConversation id (taskId), from get_job_apply_client_status

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false but say nothing about scope or side effects, and the description fills that gap: running jobs stop now, queued ones are never applied, one-click applications leave the run, and filled pages are preserved so work can be resumed. It also discloses the hard prerequisite (desktop app signed in and open, background operation allowed, offline/outdated failure mode) and the required scope. The only shortfall is that it does not say whether a stopped application can be re-queued versus only continued via instruction.

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-loaded with the purpose, then mode semantics, then state persistence, then prerequisites and auth — a sensible ordering. It is dense and information-rich rather than padded, though the long parenthetical about one-click apply and the prerequisite clause make the middle section harder to scan than it needs to be.

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 one-parameter mutation tool with no output schema, everything an agent needs is present: side effects, what is and is not undone, the follow-up tool for resuming, the environmental prerequisite, and the auth scope. The return value is characterized ('state read back after stopping') as far as is needed without an output schema.

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

Parameters5/5

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

Schema coverage is already 100% for taskId and the schema names its source tool, so the baseline would be a 3. The description goes well beyond that by explaining the semantic difference between supplying and omitting taskId, which is the single most consequential fact about this parameter and is absent from 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?

Opens with a specific verb and resource ('Stop what the apply AI is doing') and anchors it to a concrete user action ('the same as the user pressing Stop in the app'). It then splits the behavior by parameter presence, so an agent can distinguish the scoped form from the Stop-all form without consulting anything else.

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?

Explicitly defines both invocation modes: with taskId only that conversation stops, without taskId it behaves like Stop all plus every other running conversation. It also names the alternative path for continuing work later (send_job_apply_instruction), leaving no inference needed about when to resume versus stop.

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