Find potential referrers at a company for a specific job. Returns people who might be able to refer you based on your network and the job.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | The job ID to find referrers for | |
| limit | No | Maximum number of referrers to return (default: 2, max: 2) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It explains what the tool returns ('people who might be able to refer you') and the basis for selection ('based on your network and the job'), which adds behavioral context beyond just the action. However, it does not mention that the operation is read-only, or disclose any limitations, privacy, or data source details, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that begins with the verb and conveys the core purpose immediately. Every phrase adds value, with no redundancy or extraneous detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only tool with two parameters and no output schema, the description provides a clear high-level understanding of what is returned. It mentions the result type ('people') and the criteria, which is sufficient for an agent to invoke the tool. It does not detail the structure of the returned data, but that is not critical given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides complete descriptions for both parameters (jobId and limit) with 100% coverage. The tool description does not add extra meaning beyond the schema, other than reinforcing that referrers are found for a specific job. This matches the baseline for full schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Find') and the resource ('potential referrers at a company for a specific job'). It distinguishes itself from sibling tools like get_application_referrers (which targets applications) and get_job_recruiters (recruiters rather than referrers) by specifying the exact scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the usage context ('for a specific job') and the network-based selection, but it does not explicitly state when to use this tool over alternatives, nor does it mention exclusions or prerequisites. For a simple read tool, the context is reasonably clear, but it lacks explicit differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action. Tools like get_job vs get_application vs get_job_hunt are clearly separated, and match_jobs vs search_jobs are well-differentiated by saved vs explicit filters. No two tools appear to do the same thing.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_job_hunt, list_applications, update_salary). Even longer names like add_job_to_applications maintain the convention with clear, predictable structure.
With 35 tools, the server exceeds the 25+ threshold that indicates an overly large surface. While the breadth covers a comprehensive job search workflow, the number is likely overwhelming and could be consolidated without losing functionality.
The tool set covers the full job hunt lifecycle: creating hunts, searching/matching jobs, applying, tracking applications, managing resumes (including AI-generated versions), outreach, interviews, profile, and compensation. There are no obvious dead ends; update and delete operations are available where needed.
