Skip to main content
Glama
astandrik

Local YDB MCP

by astandrik
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

local_ydb_start_dynamic_node

Idempotent

Start the primary dynamic tenant node for an existing CMS tenant after creation or when resources are pending, with preflight image checks for safe operation.

Instructions

Start the configured primary dynamic tenant node for an existing CMS tenant. Before returning or executing a plan, it rejects a primary name that aliases the static container and ports that collide in the shared network namespace, including static IC port 19001. After checking that the image is present, it runs the full check-only static compatibility preflight, including the current image ID, immediately before the dynamic container start; a mismatch fails closed and requires destroy followed by bootstrap. The dynamic container is created but not started until its resolved image ID matches the static container, closing a concurrent named-tag refresh race. Use after local_ydb_create_tenant or when admin status is PENDING_RESOURCES; use local_ydb_add_dynamic_nodes for extra nodes. Without confirm=true this returns a plan only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmNoMust be true to execute planned commands. Omit or false for plan-only output.
profileNoNamed profile from local-ydb.config.json. Defaults to config.defaultProfile.
configPathNoAbsolute path to an explicit local-ydb config file. Missing, unreadable, oversized, or invalid explicit files fail closed instead of using defaults.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 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
  2. Addedv0.1.13
  3. Removedv0.1.12
  4. Addedv0.1.5
  5. Removedv0.1.4
  6. Changed3 schema fields changedv0.1.1
    • changedInput schema / properties / configPath / description
      Previous value: -"Explicit local-ydb config file path to load for this tool call."New 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."
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to execute commands. Omit or false for plan-only output."New value: +"Must be true to execute planned commands. Omit or false for plan-only output."
    • addedInput schema / properties / profile / description
      Added value: +"Named profile from local-ydb.config.json. Defaults to config.defaultProfile."
  7. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

The description goes far beyond annotations, disclosing rejection conditions (name aliasing, port collisions including 19001), execution order (preflight before start), and a specific race-condition mitigation (container created but not started until image ID matches). It also states the fail-closed destroy-and-bootstrap requirement. 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.

Conciseness5/5

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

The description is dense but every sentence adds unique operational value: purpose, validation guards, preflight, race handling, prerequisites, sibling distinction, and confirm behavior. It is front-loaded with the purpose and structured logically from validation to execution.

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?

The description covers prerequisites, failure modes, race handling, and plan mode, which is substantial for a tool without an output schema. It does not describe the exact shape or content of the returned plan, but it does clarify the plan-versus-execute distinction, leaving only minor uncertainty about return details.

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. The description adds meaningful semantics for the confirm parameter by explicitly stating "Without confirm=true this returns a plan only," which complements the schema's plain boolean description. Profile and configPath are already well covered by their schemas.

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: "Start the configured primary dynamic tenant node for an existing CMS tenant." It clearly differentiates from siblings by explicitly naming local_ydb_add_dynamic_nodes as the tool for extra nodes, so an agent can disambiguate immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage context: "Use after local_ydb_create_tenant or when admin status is PENDING_RESOURCES; use local_ydb_add_dynamic_nodes for extra nodes." It also specifies the plan-vs-execute behavior through confirm=true, making it clear when the tool merely plans versus when it acts.

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