Roman Kryvolapov Engineering Blog

Search the blog

search

Read-only

Search the romankryvolapov.com engineering blog: articles on Java, Kotlin, Android, Spring, microservices, gRPC, Kubernetes, databases, and running large language models locally (llama.cpp, LoRA fine-tuning, RAG, prompt engineering). Every article exists in English, Russian and Ukrainian, and results come in one language: set lang to the user’s language, otherwise it is guessed from the query. Returns matching articles with snippets and URLs; read one with fetch, passing its id.

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": "search"
  }
}

Input Schema

Name	Required	Description
`lang`	No	Language of the articles to return: en, ru or uk — normally the user’s language. Without it: English for a query in Latin script, Russian or Ukrainian for one in Cyrillic.
`limit`	No	How many articles to return.
`query`	Yes	Free-text search query, in any of the three languages.

Output Schema

Name	Required	Description	Default
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds real value on top: results are returned in exactly one language, the language is otherwise guessed from the query, and results include snippets and URLs plus an id for fetch. It does not describe result ranking or empty-result behavior, keeping it at 4.

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?

Front-loaded with purpose, then language behavior, then return shape and next step — a logical order with no filler. The topic list is a bit long but serves retrieval routing, so it mostly earns its place.

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 an output schema present, the description need not explain return values, yet it briefly does (snippets, URLs, id) which is harmless. For a 3-parameter search tool with full schema coverage and annotations, the description is complete enough to call correctly; only edge cases like zero results are unaddressed.

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%, so query, lang and limit are fully documented in the schema, including lang's fallback heuristic. The description only repeats the lang guidance ('set lang to the user's language') and adds nothing about limit or query syntax; baseline 3 is appropriate.

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 opens with a specific verb and resource ('Search the romankryvolapov.com engineering blog') and scopes the corpus by topic (Java, Kotlin, Android, gRPC, LLMs, etc.), so an agent can distinguish it from fetch/get_page without opening any schema.

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 states the search context (free-text query in any of three languages) and routes to the sibling for follow-up ('read one with fetch, passing its id'). It lacks an explicit statement of when NOT to use it (e.g. use get_page for non-article content), so it falls short of a 5.

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

All Roman Kryvolapov Engineering Blog 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?