PERM Tracker

Find a job's SOC code

find_soc_code

Read-onlyIdempotent

The SOC occupation codes employers filed a job title under in DOL's PERM, prevailing wage and LCA files, with each code's share of the title's filings. Or a code's title, and for a 2010 code the 2018 codes it became. Examples: {"query": "data scientist"} or {"query": "15-1132"}.

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": {
      "query": "<query>"
    },
    "name": "find_soc_code"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	A job title or a SOC code, e.g. data scientist or 15-2051.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already establish this as a read-only, idempotent, closed-world lookup, so the description's job is to add substance, which it does: results include each code's share of the title's filings, and the tool also performs a reverse code-to-title lookup plus a 2010-to-2018 code crosswalk. That is real disclosure about result content that the annotations cannot convey. It stops short of describing ranking, truncation, or how many codes are returned.

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?

It is compact and the examples are well placed at the end, but the opening sentence is front-loaded with a long noun phrase and the follow-on fragment about 2010 codes disrupts the parse. A cleaner split into 'what it returns' and 'what you can query' would earn back points.

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?

With no output schema, the description carries the burden of explaining return values, and it does describe them: codes with filing shares in one direction, a title in the other, and a vintage crosswalk. For a single-parameter lookup tool this is close to complete; only result cardinality and ordering are left unstated.

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 100% and the schema already states 'A job title or a SOC code, e.g. data scientist or 15-2051,' which is nearly identical to the description's examples. The only added semantic is that a 2010-vintage code yields the 2018 codes it became, but that is framed as a result behavior rather than guidance on how to phrase the query. 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?

The description names the specific resource (SOC occupation codes) and the data sources (DOL PERM, prevailing wage, LCA files), and it covers both lookup directions, which none of the sibling tools do. The second sentence fragment 'Or a code's title, and for a 2010 code the 2018 codes it became' is grammatically broken, so the reverse-lookup mode has to be inferred rather than read cleanly.

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

Usage Guidelines3/5

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

The two worked examples ({"query": "data scientist"} and {"query": "15-1132"}) implicitly tell an agent what input shapes are valid, and the mention of a 2010-to-2018 crosswalk signals a secondary use case. However, there is no explicit statement of when to reach for this tool versus search_sponsors or employer_profile, and no exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All PERM Tracker tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?