Skip to main content
Glama
Sign In
dsa-coach-mcp

dsa-coach-mcp

by aaryagodbole
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

record_problem

Capture a problem from a platform without an adapter using its page URL, title, tags, and stated difficulty, and return the platform and problem ID for review logging.

Instructions

Record a problem from a platform this server has no adapter for, as read from its page: its URL, title, the tags the page shows and its difficulty as the page states it. The platform is the URL's host, and the problem id its path. Returns the platform and problem_id to pass to log_review.

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": {
      "url": "<url>",
      "title": "<title>"
    },
    "name": "record_problem"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
tagsNo
levelNo
titleYes

Output Schema

NameRequiredDescriptionDefault
urlYes
tagsNo
levelNo
titleYes
sourceNoplatform
platformYes
problem_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare this is a non-readonly, non-idempotent, non-destructive write. The description adds the derivation rule for platform and problem_id, but it never addresses what happens when the same URL is recorded twice, which matters given idempotentHint=false, nor does it mention any prerequisites or side effects.

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?

Three sentences, front-loaded with the action and scope, with no filler. Slightly dense phrasing ('as read from its page', 'as the page states it') costs a little parsing clarity but no wasted sentences.

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?

An output schema exists and annotations cover the safety profile, so the description only needs the write's intent and derivations, both of which are present. The one real gap is duplicate/staleness behavior for a non-idempotent recorder.

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%, so the description has to carry the parameter burden, and it mostly does: url is decomposed into host=platform and path=problem_id, tags are the tags shown on the page, and level is the difficulty the page states. Only level's expected format remains undefined beyond 'as the page states it'.

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?

The description gives a specific verb and resource ('Record a problem') and immediately narrows scope to platforms with no adapter, which separates it from search_problems and list_platforms. It also explains how the platform/problem_id are derived from the URL, so the agent knows exactly what gets stored.

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?

It clearly signals the trigger condition ('a platform this server has no adapter for') and names the downstream step by saying the returned platform and problem_id are meant for log_review. It stops short of an explicit exclusion, e.g. telling the agent to check list_platforms first and use a different tool when an adapter does exist.

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