bulk_insert_records

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

Annotations declare only that this is a non-idempotent write (readOnlyHint=false, idempotentHint=false), and the description adds substantial context on top: asynchronous execution, the wait window and what is returned when the job is still running, the returned jobId/state/processed/failed counts plus up to 10 sample failures, and the important side effect that null values are written as #N/A and clear a field. The #N/A field-clearing detail is exactly the kind of mutation consequence an agent needs and structured fields do not convey.

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-loaded with purpose and mode in the first clause, then constraints, then return shape, then the insert-specific caveat, which is a sensible ordering. It is a single dense paragraph where several phrases duplicate the schema's own limit text, costing a little efficiency.

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 multi-mode write tool with no output schema, the description covers what is missing elsewhere: return payload contents, async continuation paths (bulk_job_status, bulk_job_results), input-mode selection, and the null/#N/A side effect. An agent has enough to invoke it correctly without opening other tools beyond the explicitly named follow-ups.

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?

The nested schema does describe parameters well, and the description reinforces the highest-risk semantics: the 'exactly one of records/csvPath/csvContent' exclusivity rule and the size ceilings (2000 inline records, 10 MB CSV text). It largely restates the schema's own limits rather than adding new meaning, so it earns credit but not a top score.

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 states a specific verb and resource ('Insert many records with the Bulk API 2.0') plus its operational mode ('asynchronous, for large volumes'), which immediately separates it from bulk_update_records and bulk_upsert_records. The trailing instruction 'Do not include Id values for inserts' further reinforces the insert-vs-update boundary.

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?

It gives clear routing guidance: name bulk_job_results for full result files, name bulk_job_status (via schema) for continued polling, and spell out the mutually exclusive choice among records/csvPath/csvContent with the conditions that select each. It never explicitly contrasts itself with bulk_upsert_records, so the sibling selection guidance is implied rather than complete.

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