Manage SQL warehouses

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

Annotations only say destructiveHint=true/openWorldHint=true globally; the description adds a per-action safety classification (READ_ONLY/WRITE/DESTRUCTIVE), the confirmation gate and its 'reviewed plan / confirmation_required' precondition, and the production-warehouse refusal rule. That is materially more behavioral context than the annotations carry.

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?

Information is front-loaded into an action list followed by a safety classification, both quick to scan. The inline JSON spec example adds length but earns its place by showing required field names and casing; still slightly dense for a single paragraph.

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?

With an output schema present, return-value detail is unnecessary, and the description covers the action set, destructive prerequisites, and mutation semantics. The one soft spot is that list pagination or error/refusal response shape is left entirely to the schema.

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 already 89%, so the baseline is 3; the description goes beyond it by explaining the spec object's field names and merge semantics for update, and the confirm workflow. It does not add much on wait/timeout/pagination beyond what the schema descriptions state.

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?

States a specific verb and resource and then enumerates every supported action (list, get, create, update, start, stop, delete), so an agent knows exactly what surface this tool covers. The scope is distinct from generic compute/warehouse siblings, and the create spec example makes the capability concrete.

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?

Gives clear per-action conditions: spec is required for create, update's spec holds only changed fields and is merged onto the current config, stop/delete need confirm=true and are refused for production warehouses. It does not explicitly route against sibling tools like manage_warehouse or list_compute, so an alternative-selection note is missing.

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