bulk_hard_delete_records

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

With annotations already declaring destructiveHint/idempotentHint, the description still adds substantial behavior: records bypass the Recycle Bin and are unrecoverable, a specific permission ('Bulk API Hard Delete') is required, and the confirmation flow (client prompt, typed 'confirm' string, refusal on omission) is spelled out. These are exactly the safety-critical traits an agent needs before invoking a destructive call.

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?

Front-loads the irreversibility and permission requirement before the mechanical input rules, which is the right ordering for a destructive tool. The closing sentence on confirmation-prompt behavior is slightly tangled but still earns its place.

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, async bulk operation with no output schema, the description covers the danger profile, permissions, input-source selection, confirmation gating, and points to bulk_job_status for follow-up on still-running jobs. Nothing an agent needs in order to call it correctly is missing.

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 description coverage registers as 0%, so the description must carry the load, and it does: it states the exactly-one-of constraint over ids/csvPath/csvContent, the CSV 'Id' column expectation, and the exact 'HARD DELETE <sobject>' confirm format. It adds real meaning beyond a bare property list, though it does not cover the wait/targetOrg fields.

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 ('PERMANENTLY delete many records') and names the exact underlying operation (Bulk API 2.0 hardDelete). The phrase 'bypass the Recycle Bin and cannot be restored' implicitly distinguishes it from the sibling bulk_delete_records, so an agent can route between the two without opening either schema.

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 conditional guidance for the input modes (use csvPath for files already on disk, csvContent for files uploaded into a sandboxed client) plus the permission prerequisite and confirmation gate. It does not explicitly name bulk_delete_records as the non-permanent alternative, so the when-not decision is left to inference.

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