Skip to main content
Glama
Sign In
contest-mcp

contest-mcp

by mytrashcan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

check_eligibility

Compares a contest posting's eligibility rules against your stored profile and returns pass, fail, or unknown verdicts for school, region, age, status, and team criteria.

Instructions

공고의 응모 자격을 프로필(~/.contest-mcp/profile.json)과 대조해 축별로 판정한다.

판정은 pass/fail/unknown 세 가지이며, 원문 문장 근거가 있을 때만 pass/fail을 준다. 학교·지역(주민등록지 기준)·나이·신분·팀 구성 5축을 본다. 프로필이 없으면 unknown이 정상이다.

Args: ident: contest id, 상세 URL, 또는 ix·contest_pk.

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": {
      "ident": "<ident>"
    },
    "name": "check_eligibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
identYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses that the output space is pass, fail, or unknown, that pass or fail is emitted only when there is supporting source-sentence evidence, and the axes it evaluates. It does not state the shape of the per-axis result, the number of calls, or the behavior when `ident` fails to resolve, leaving some behavioral gaps for a tool without annotations.

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?

It is front-loaded with the purpose, followed by output semantics, axes, and the profile fallback; every sentence adds information. The trailing Args block is slightly redundant given how briefly the identifier is described, but nothing is wasteful.

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

Completeness5/5

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

The description covers the precondition for a profile, the three-valued output, the evidence rule, the five axes, and the expected no-profile outcome, so despite having no output schema and no annotations, an agent has enough information to call it and interpret results correctly.

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 description coverage is 0% for the single `ident` parameter, so the description must compensate, and it does: it says the value may be a contest id, a detail URL, or an ix or contest_pk. That is the key ambiguity resolved; only the exact accepted format or examples are missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compare/judge eligibility) and resource (공고의 응모 자격) and enumerates the five axes it evaluates (school, region, age, status, team). This is unmistakably different from siblings like get_contest or search_contests, which only retrieve contest data.

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?

The description makes the precondition explicit (needs `~/.contest-mcp/profile.json`) and tells the agent that receiving `unknown` is the expected outcome when no profile exists, which should prevent pointless retries. It does not enumerate alternatives or state explicitly when not to call it, so it falls short of a full 5.

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