Skip to main content
Glama

Add a job to the job tracker

trackApplication
Idempotent

Add a job to the candidate's job tracker as a draft. Give exactly one of:

  • jobUrl: a public posting link (Greenhouse, Lever, Ashby, company careers page…). Clera reads the page for the title, company and description, which takes up to half a minute. LinkedIn job pages can't be read; when a link is refused, add the job by hand instead.

  • jobId: an external job board listing's jobId from searchJobs, listSavedJobs or a readJobListing result with kind board, e.g. a saved job the candidate just applied to.

  • position and companyName, typed by hand, with jobDescription if the candidate pasted it.

A link that is already on the tracker returns the existing entry with created false. The job tracker also shows every Clera intro except withdrawn ones, but these tools only cover the jobs the candidate tracks themselves; listMyPipeline covers intros. Moving a card never contacts the company.

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": "trackApplication"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdNoThe jobId from a searchJobs or listSavedJobs result, or a readJobListing result with kind board.
jobUrlNo
positionNo
companyNameNo
searchFiltersNoThe job board search this job was tracked from.
jobDescriptionNo

Output Schema

NameRequiredDescriptionDefault
createdYes
applicationYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the mutation and idempotency profile is known. The description still adds real value beyond them: the half-minute page-fetch latency, the LinkedIn refusal, and the duplicate-returns-existing-entry-with-created-false behavior. However, the stray sentence "Moving a card never contacts the company" describes something unrelated to adding a job and muddies rather than clarifies.

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?

The bulleted enumeration of the three input modes is well front-loaded and each bullet earns its place. The closing privacy/recording notice and the unrelated card-moving sentence are filler relative to the tool's job, costing a point.

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 6-parameter, open-world mutation with an output schema, the description covers the decision-relevant surface: input modes, duplicate handling, latency, and a cross-tool pointer for intros. The main residual gap is whether searchFilters is meant to accompany a manual entry, which the description never addresses.

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 only 33% and all six parameters are optional, so the mutual-exclusivity constraint the description spells out is genuinely load-bearing — it cannot be expressed in the schema. It also explains what jobUrl vs jobId vs position+companyName mean in practice. The large nested searchFilters object is left unexplained by the description, relying entirely on its own one-line schema text.

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?

The description opens with a concrete verb and resource — "Add a job to the candidate's job tracker as a draft" — and enumerates the three input modes (jobUrl, jobId, position+companyName). It also clarifies the tracker's scope versus intros by pointing at listMyPipeline. It stops short of distinguishing itself from the closely-named sibling saveJob, leaving an ambiguity an agent must resolve elsewhere.

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 states the selection rule explicitly ("Give exactly one of:") and defines when each mode applies, including where a jobId legitimately comes from (searchJobs, listSavedJobs, readJobListing with kind board). It also gives a concrete failure path: LinkedIn pages can't be read, so add the job by hand instead.

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