bulk_create_records

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

Adds important behavior details beyond annotations: rollback deletes on failure, all-or-nothing, dry_run support. Annotations only provide readOnlyHint=false, so description fills gaps well.

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?

Three front-loaded sentences with no wasted words, clearly conveying key points.

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?

Covers core aspects: bulk creation, rollback, dry_run, requirement. Could mention size limits but still complete given no output 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 covers 100% but description adds context on batch behavior and rollback token, enhancing understanding beyond schema descriptions.

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 explicitly states it creates many records in a single call, tracking sys_ids and returning a rollback token, distinguishing it from siblings like create_record.

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?

Mentions dry_run, rollback_on_error, and requirement WRITE_ENABLED=true, but doesn't explicitly say when to use vs single create or alternatives.

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