Skip to main content
Glama

Apply

hunt_apply
Destructive

Record an application actually submitted. One per posting. One application per posting (JH-4) — the duplicate guard exists so the SAME role through two agencies gets a decision, not two submissions. applied_at accepts the literal "unknown" when the submission is real but the date was never recorded — never guess a date (JH-1). Record the resume version that actually went out (JH-10). Effects: application created; posting -> applied; submission logged as a touch.

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": {
      "posting_id": "<posting_id>"
    },
    "name": "hunt_apply"
  }
}

Input Schema

NameRequiredDescriptionDefault
channelNo
applied_atNoISO date, or the literal "unknown" — never a guess (JH-1).
posting_idYesThe posting.
via_contactNoRecruiter who submitted, e.g. HC-0001 — for the double-submission audit.
resume_versionNoWhat was actually sent — label or id (JH-10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare a destructive, non-idempotent write, and the description adds real value beyond them: the concrete state effects ('application created; posting -> applied; submission logged as a touch') and the one-per-posting duplicate behavior. It does not say whether these effects are reversible or how a rejected duplicate is surfaced, which keeps it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and reasonably short, but 'One per posting' is immediately repeated as 'One application per posting (JH-4)' with the same content. The parenthetical rule codes (JH-4, JH-1, JH-10) are opaque unless the agent already knows the rulebook.

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 mutation tool with no output schema, the definition covers trigger, effects, duplicate policy, and the date-accuracy rule well enough to call correctly. The missing piece is how a duplicate rejection or partial failure is reported back to the agent.

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 80% and already documents applied_at's 'unknown' literal and resume_version's intent, so the description largely restates them. channel and via_contact are not mentioned at all in the description, adding no compensating meaning. Baseline 3 is appropriate.

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: 'Record an application actually submitted,' plus the cardinality constraint 'One per posting.' This distinguishes it from a mere status change, but it never names the nearby alternatives (e.g., correcting an application or setting status), so sibling differentiation is left implicit.

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

Usage Guidelines4/5

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

Gives a clear trigger ('actually submitted') and an explicit prohibition ('never guess a date'), plus the reasoning behind the duplicate guard. It stops short of saying when to use a different tool instead, so no explicit alternative routing.

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.