Data: import

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description carries the rest and does so well: it reads a local file, creates one record per row, validates against field types, rejects unknown columns unless ignore_unknown is set, ignores system columns, and never updates existing records. That is substantial behavioral context beyond the annotations.

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 tightly packed sentences with the safety protocol front-loaded and no filler. Minor friction: it references a '--yes' flag that has no corresponding schema parameter, which could momentarily confuse an agent mapping prose to inputs.

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 7-parameter mutation tool with no output schema and only safety annotations, the description covers the important semantics: validation, row rejection, system-column handling, and the mandatory dry-run flow. The only gaps are the concurrency setting and the errors-file return behavior, which are minor for a create-only import.

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 100%, so baseline is 3. The description does add meaning for a few parameters (dry-run validation, dropping unknown columns, format inference), but it never mentions concurrency or the errors output-file behavior, so it does not meaningfully exceed what the schema already documents.

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?

Opens with a precise verb and resource ('Create records from a CSV, JSON array or JSONL file') and immediately scopes the operation as bulk/one-record-per-row. It also names the sibling it is not ('For a single record, use data_create'), 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 explicit procedural guidance ('Always run with --dry-run first and only add --yes after the dry run is approved') plus an explicit alternative for the single-record case (data_create). Both the when-to-use and the when-to-use-something-else cases are covered.

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