Skip to main content
Glama
Sign In
jobinja-mcp

jobinja-mcp

by sepehr071
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Salary statistics

jj_salary_stats
Read-onlyIdempotent

Estimates monthly salaries in Toman from top job search results, summarizing stated minimum pay across a sample of ads; filter by keyword, category, province, experience, or remote.

Instructions

Estimate monthly salaries (Toman) from the ad pages of the top search results.

Summarises stated minimums of sample ads; most say negotiable, so check n_with_salary. A sample, not a survey.

Input Schema

NameRequiredDescriptionDefault
remoteNoOnly remote jobs.
sampleNoAds to read (one request each).
keywordNoTitle/text words.
categoryNoSame as jj_search_jobs.
provinceNoSame as jj_search_jobs.
experienceNoExperience.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv0.2.0
    • removedInput schema / properties / category / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • changedInput schema / properties / category / description
      Previous value: -"Job category (see jj_filters)."New value: +"Same as jj_search_jobs."
    • addedInput schema / properties / category / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / experience / anyOf
      Removed value: -[
-  {
-    "enum": [
-      "any",
-      "under_2",
-      "3_6",
-      "7_plus"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • addedInput schema / properties / experience / enum
      Added value: +[
+  "any",
+  "under_2",
+  "3_6",
+  "7_plus",
+  null
+]
    • addedInput schema / properties / experience / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / keyword / anyOf
      Removed value: -[
-  {
-    "maxLength": 100,
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • changedInput schema / properties / keyword / description
      Previous value: -"Words in the title or text, e.g. python."New value: +"Title/text words."
    • addedInput schema / properties / keyword / maxLength
      Added value: +100
    • addedInput schema / properties / keyword / type
      Added value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / province / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
    • changedInput schema / properties / province / description
      Previous value: -"Province name (see jj_filters)."New value: +"Same as jj_search_jobs."
    • addedInput schema / properties / province / type
      Added value: +[
+  "string",
+  "null"
+]
    • changedInput schema / properties / sample / description
      Previous value: -"How many ads to read (each is one request)."New value: +"Ads to read (one request each)."
  2. First observedv0.1.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower, but the description adds useful behavior: results come from individual ad pages, coverage is partial because most ads say negotiable, and the agent should inspect n_with_salary before trusting the figures. That is genuine caveat information not present in structured fields; it stops short of stating request cost or latency, which only the schema hints at.

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?

Two short sentences, front-loaded with the core verb and resource, with the data-quality caveat second. It is efficient and waste-free, though "check n_with_salary" is slightly cryptic given there is no output schema to explain that field.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Good coverage of purpose and the negotiable-salary caveat for a no-output-schema tool, but n_with_salary is referenced without definition and there is no indication of cost (sample ads are fetched one request each, up to 30) or result shape. An agent can call it, but may misread the returned statistics.

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 description coverage is 100%, so the schema already explains every parameter including the sample cap and enum. The description adds only the framing that parameters scope which ads are read ("top search results"), which is marginal but consistent; baseline 3 applies.

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, resource, currency unit and data source: "Estimate monthly salaries (Toman) from the ad pages of the top search results." That is clearly distinguishable from the listing-oriented siblings (jj_search_jobs, jj_market), though it never names a sibling explicitly.

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?

Use is implied by the estimate framing plus the caution "A sample, not a survey", which tells the agent this is for rough salary ranges rather than exhaustive data. There is no explicit when-not guidance and no pointer to jj_search_jobs or jj_market as alternatives when the agent actually wants listings rather than an estimate.

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

Deploy Server

Other Tools