local_ydb_restart_stack

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

With only sparse annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description carries full burden and exceeds it: it discloses the preflight match requirements, stop ordering (dynamic before static), unconditional node recreation, the restoration rule for unexpected containers, the unrecoverable-definition risk, and plan-only vs. executed behavior. This is richer than the annotations alone and consistent with them — recreation preserves configured definitions, matching destructiveHint=false.

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

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

The description is a single dense run-on paragraph with many compound clauses, making it difficult to parse despite containing valuable detail. It is not front-loaded beyond the first sentence and lacks any bulleted structure or sentence-level separation of concerns (preflight, ordering, recreation, rollback). While information-dense, it sacrifices readability for completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a highly complex orchestration tool with no output schema, the description documents the critical operational aspects: preflight validation criteria, container stop order, recreation guarantees, restoration of unexpected containers, rollback strategy, and plan-mode behavior. The only gap is that the returned plan's exact contents are not specified, but overall it is comprehensive for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 value by mapping the confirm parameter to observable behavior ('Without confirm=true this returns the restart plan only'), which clarifies the plan vs. execute semantics beyond the schema's 'Must be true to execute planned commands.' profile and configPath are adequately defined in schema and need no additional description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb-resource pair: 'Reconcile and restart the selected profile' after an inventory and check-only preflight. This clearly differentiates it from siblings like local_ydb_destroy_stack (destructive teardown) and local_ydb_bootstrap (initial setup), since restart is a reconciliation/re-creation operation on an existing stack.

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

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

The description provides clear contextual guidance by stating when the tool does NOT apply ('configured binding changes require destroy followed by bootstrap') and what happens in plan vs. execute mode. It also references rollback via 'restart or bootstrap reconciliation.' However, it never names sibling tools explicitly as alternatives (e.g., 'use destroy_stack for X'), leaving some of the when-to-use decision implicit.

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