local_ydb_remove_dynamic_nodes

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial behavioral context beyond them: the primary dynamicContainer is always protected, removal is highest-suffix-first, explicit selectors create runtime drift, and there are concrete rollback strategies. This is exactly the kind of safety-relevant detail an agent needs before invoking a destructive tool, and it contradicts no annotation.

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?

Five sentences, each carrying distinct, non-redundant information: core action, default selection rule, drift warning, rollback guidance, and protected resource. The purpose is front-loaded and no sentence is filler. For a destructive tool with 7 parameters and no output schema, this density is warranted rather than bloated.

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 no output schema, the description covers action, default behavior, edge cases, rollback, and protection. The qualifier "when the node IC port can be resolved" raises an unresolved question — what happens when it cannot be resolved? — which is a minor gap. Overall, however, an agent has enough to invoke this tool correctly and understand its failure-recovery story.

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, but the description adds genuine cross-parameter interaction semantics: the eligibility rule when all selectors are omitted, the startIndex default interplay ("defaults to profile.dynamicNodeCount + 1"... "Explicit selectors default to 2"), and the drift risk when selectors target configured suffixes. These relationships are not visible in the schema alone.

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 description opens with a specific verb+resource pair — "Remove dynamic tenant suffix nodes one at a time" — and adds a concrete verification outcome ("verify nodelist disappearance"). This clearly differentiates it from siblings like local_ydb_add_dynamic_nodes and local_ydb_start_dynamic_node, which are creation/start operations, while this is the removal counterpart. The scope is unambiguous.

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 gives clear context for when the default mode is safe ("Without containers, nodeIds, or startIndex, only one-off suffixes above profile.dynamicNodeCount are eligible") and warns of the drift consequence of explicit selectors. It names add_dynamic_nodes as the rollback path for one-off nodes and bootstrap/restart for configured nodes. It lacks an explicit 'use X instead of Y' directive, but the conditions and consequences are well-specified.

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