local_ydb_destroy_stack

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

Annotations already declare destructiveHint=true, so the safety profile is known. The description adds value by specifying WHAT gets destroyed (tenant metadata, containers, network, storage) and the optional host-path cleanup semantics. But it doesn't describe what exactly happens to shared resources, whether the action is reversible, or how the plan-only output looks before confirm. Given destructive annotations coverage, a 3 is fair.

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?

Single sentence, front-loaded with the primary action and scope. Zero wasted words. The optional host-path cleanup is appended at the end as a modifier, which is appropriate since it's secondary to the main destructive action.

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 destructive tool with good annotation coverage (destructiveHint=true) and 100% schema param documentation, the description is near-complete. It names all major resource types destroyed and the optional cleanup dimension. A small gap: it doesn't mention the confirm-required behavior explicitly, but the schema covers that. Given no output schema needed and rich annotations, this is well-covered.

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 schema already documents all 6 parameters well. The description adds value by clarifying the overall effect (containers, network, storage removal) and that host-path cleanup is OPTIONAL, which helps the agent understand the relationship between the destroy action and the removeDumpHostPath/removeBindMountPath/removeAuthArtifacts flags. Slight redundancy with schema exists but the description frames the optionality meaningfully.

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?

Description clearly states the verb (remove/destroy) and resource (tenant metadata, local-ydb containers, network, storage, host-path) with explicit scope for a 'profile'. It distinguishes from siblings: local_ydb_cleanup_storage is partial cleanup, remove_dynamic_nodes is narrower, while this is full-stack teardown. The inclusion of 'optional host-path cleanup' adds meaningful scope detail.

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 and param docs convey when to use it: full teardown of containers, network, storage for a profile. The 'confirm' parameter implicitly conveys a plan-only mode vs execution mode. However, it doesn't explicitly name alternative tools (e.g., local_ydb_cleanup_storage for storage-only) or state when NOT to use it, so it misses the explicit exclusions bar for a 5.

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