Skip to main content
Glama
astandrik

Local YDB MCP

by astandrik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

local_ydb_healthcheck

Read-onlyIdempotent

Run a read-only healthcheck for a YDB tenant or root database using the official SelfCheck path, returning issue counts, types, capped raw output, and overall health status.

Instructions

Read-only YDB monitoring healthcheck for the configured tenant or root database. Uses the official YDB CLI SelfCheck path, returns selfCheckResult, issue counts, issue types, capped raw output, and whether the database is healthy; a requested noCache/noMerge option rejected with the exact recognized two-line legacy parser signature is reported through optionResolution and warnings, while compatibilityFallback says whether a retry actually started. Use after local_ydb_status_report for database-level diagnostics.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noCacheNoRequest cache-bypass semantics for this healthcheck. Newer YDB CLIs receive --no-cache. A rejection matching the exact recognized two-line legacy parser signature is recorded in optionResolution and warnings; when the shared deadline permits an actual retry without that option, compatibilityFallback is true.
noMergeNoRequest unmerged healthcheck issue entries. Newer YDB CLIs receive --no-merge. A rejection matching the exact recognized two-line legacy parser signature is recorded in optionResolution and warnings; when the shared deadline permits an actual retry without that option, compatibilityFallback is true.
profileNoNamed profile from local-ydb.config.json. Defaults to config.defaultProfile.
maxIssuesNoMaximum number of issue_log entries returned in the issues field. Counts still cover the full response. Defaults to 100.
timeoutMsNoServer-side YDB healthcheck timeout in milliseconds. Defaults to 120000.
configPathNoAbsolute path to an explicit local-ydb config file. Missing, unreadable, oversized, or invalid explicit files fail closed instead of using defaults.
databasePathNoYDB database path to check. Defaults to the configured tenant path; only the configured tenant path or root database path are accepted.
maxOutputBytesNoMaximum UTF-8 bytes returned per raw stdout/stderr stream. Defaults to 65536.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.21
    • changedInput schema / properties / configPath / description
      Previous value: -"Explicit local-ydb config file path to load for this tool call. Useful when the MCP server should pick up a different config without restart."New value: +"Absolute path to an explicit local-ydb config file. Missing, unreadable, oversized, or invalid explicit files fail closed instead of using defaults."
    • addedInput schema / properties / configPath / minLength
      Added value: +1
    • changedInput schema / properties / noCache / description
      Previous value: -"Pass --no-cache to force YDB to bypass cached healthcheck results."New value: +"Request cache-bypass semantics for this healthcheck. Newer YDB CLIs receive --no-cache. A rejection matching the exact recognized two-line legacy parser signature is recorded in optionResolution and warnings; when the shared deadline permits an actual retry without that option, compatibilityFallback is true."
    • changedInput schema / properties / noMerge / description
      Previous value: -"Pass --no-merge to keep individual YDB healthcheck issue records separate."New value: +"Request unmerged healthcheck issue entries. Newer YDB CLIs receive --no-merge. A rejection matching the exact recognized two-line legacy parser signature is recorded in optionResolution and warnings; when the shared deadline permits an actual retry without that option, compatibilityFallback is true."
  2. Addedv0.1.13
  3. Removedv0.1.12
  4. Addedv0.1.9

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond that: it uses the official SelfCheck path, returns selfCheckResult/issue counts/issue types/capped raw output/health, and details the noCache/noMerge legacy-parser rejection flow through optionResolution, warnings, and compatibilityFallback retry semantics. No contradiction with 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?

Three dense sentences, front-loaded with purpose and scope, with every sentence contributing. The middle sentence is overloaded with nested clauses about noCache/noMerge rejection and retry semantics, making it harder to parse than necessary, but there is no filler.

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?

Even without an output schema, the description enumerates the key return categories (selfCheckResult, issue counts, issue types, capped raw output, health), the option fallback signals, and the recommended usage chain. The 8 parameters are fully specified in the schema, so nothing needed to invoke the tool correctly is missing.

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 description coverage is 100%, so the schema carries the parameter semantics. The tool description reinforces the noCache/noMerge fallback behavior but does not add meaning beyond the parameter descriptions already present; the baseline of 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 'Read-only YDB monitoring healthcheck for the configured tenant or root database', naming a specific resource and operation. It further distinguishes itself by identifying the official YDB CLI SelfCheck path and the specific return categories, and explicitly positions itself after local_ydb_status_report.

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?

'Use after local_ydb_status_report for database-level diagnostics' gives a concrete execution context and separates this tool from the status-report sibling. It does not spell out when-not-to-use alternatives or name other branches, so it stops short of a fully explicit routing rule.

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