Skip to main content
Glama

Сбросить кэш данных ВШЭ

hse_clear_cache
Idempotent

Clears cached LMS and ELK query results so subsequent requests return up-to-date data, such as immediately after submitting an assignment or application. Scope can limit the reset to one service.

Instructions

Результаты тулов lms_*/elk_* и сводок my_today/my_week/my_deadlines (они собираются из тех же ресурсов) кэшируются в памяти на 2–30 минут, чтобы не открывать браузер заново ради неизменившихся данных. Если нужно гарантированно свежее значение — например, сразу после подачи работы или заявки, — вызовите этот тул, затем повторите нужный запрос. scope сужает сброс до одного сервиса.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hse_clear_cache"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoЧто сбросить: all (по умолчанию) или один сервис

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.2
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv0.1.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only say it is non-read-only but idempotent and non-destructive; the description adds the real behavioral story: what is cached, the 2–30 minute TTL, that the call invalidates rather than mutates data, and that scope can narrow the effect. It does not say what the call returns or confirm there are no other side effects, but the substantive behavior is disclosed.

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 dense sentences, no filler, and the caching rationale sets up why the tool exists before the call instruction. Slightly back-loaded: the actionable 'вызовите этот тул' arrives after a long explanatory clause, but nothing is wasted.

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?

For a one-parameter maintenance tool with no output schema, the description covers what is invalidated, why, when to invoke, and what to do afterward. The only gap is that it doesn't indicate whether a confirmation or status is returned, which an agent may want before re-issuing its query.

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 enum (all/elk/lms) is already documented in the schema. The description's 'scope сужает сброс до одного сервиса' restates the enum rather than adding format, precedence, or interaction details beyond it, so the baseline 3 applies.

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?

Names the operation (cache reset), the resource (HSE tool data), and precisely enumerates the affected tools (lms_*, elk_*, and the my_today/my_week/my_deadlines summaries that share those resources). No sibling tool does this, so an agent can tell it apart from hse_changes_reset or any read tool without opening the 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?

Explicitly states the trigger condition ('если нужно гарантированно свежее значение — например, сразу после подачи работы или заявки') and gives the follow-up action (repeat the request). It also implicitly discourages routine calls by explaining the TTL exists to avoid unnecessary browser work, but there is no explicit 'do not call when' clause.

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