Skip to main content
Glama

Сбросить накопленные изменения

hse_changes_reset
DestructiveIdempotent

Clears local snapshot databases and event logs for one or all HSE areas, forcing the next changes query to rebuild state; requires confirm: true.

Instructions

Стирает локальные базы снимков и журнал событий области (или всех областей), после чего следующий hse_changes создаёт базу заново. Полный сброс (без scope) удаляет и копии повреждённого файла (state.json.corrupt-*) и оставшиеся временные файлы. Меняет только локальные файлы. Требует confirm: true.

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": {
      "confirm": "<confirm>"
    },
    "name": "hse_changes_reset"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoОбласть; без неё — все.
confirmYesДолжно быть true: подтверждение стирания.

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

A4.7/5.0
Behavior5/5

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

Goes well beyond the destructive/idempotent annotations by naming exactly what is destroyed (snapshot DBs, event log, corrupt-file copies, temp files), scoping the blast radius to local files only, and stating that recovery happens implicitly via the next hse_changes call. This is precisely the concrete destructive-behavior detail an agent needs before committing an irreversible-looking delete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core destructive action and the recovery path, then escalating detail on the full reset and the local-only scope. Nothing is redundant with the schema or annotations.

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?

For a two-parameter destructive tool with no output schema, the description covers what is deleted, what is preserved (local files only), how state is rebuilt, and the confirmation gate. Nothing an agent needs before invoking is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning about the scope parameter: omitting it means all scopes and additionally triggers deletion of corrupt-file and temp-file remnants. It restates the confirm requirement rather than adding to it, keeping it out of the 5 band.

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 and resource: wipes local snapshot databases and the scope's event log, and names the follow-on effect on hse_changes. This clearly distinguishes it from the sibling hse_changes (which builds the DB) and hse_clear_cache without needing to open 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?

Explains the operational context (next hse_changes recreates the DB) and distinguishes degraded-state reset from full reset, which effectively tells the agent when each variant applies. It does not explicitly contrast against the sibling hse_clear_cache, so it stops short of the top band.

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