create_records

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's job is to add context — and it does: computed fields must be omitted, created IDs are returned, and 'per-row isolation: a failing row is reported, not fatal' discloses non-atomic partial-failure semantics that nothing in the schema or annotations conveys. It omits any batch-size cap or retry/idempotency implications, keeping it below a 5.

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?

Four short sentences, front-loaded with the action, then the payload constraint, the return value, and the failure model. Every sentence carries information an agent would otherwise have to guess at; nothing is redundant with the title or schema.

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 5-parameter mutation tool with no output schema, the description covers the return value (created record IDs), the payload shape constraint, and the partial-failure model — the highest-risk unknowns for a batch create. Remaining gaps are the batch-size ceiling and the effect of viewId ordering, but these are secondary.

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 is 100%, so the schema already documents all five parameters and the baseline is 3. The description adds one genuine constraint beyond the schema — that computed fields are read-only and must be omitted from cellValuesByColumnId — but says nothing about viewId positioning, sourceKey, or debug.

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 opening sentence names a specific verb and resource with clear scope ('one or more'), which separates it from single-record creation and from update_records/duplicate_records in the sibling list. It stops short of naming an alternative explicitly, so the differentiation is inferable rather than stated.

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?

Usage is implied by 'create one or more records' — batch inserts go here, not to update_records. However, there is no explicit when-to-use/when-not-to-use guidance, no mention of how this differs from duplicate_records or apply_record_template, and no stated prerequisites such as required permissions or batch size limits.

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