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

Rich disclosure beyond the sparse annotations: requires auth, free, 1-500 records / 512 KB cap, the full validation pipeline (schema check, no personal data, duplicate drops, readme model screen skipped for private projects), immutable-version semantics, ~1s private merge, and points earned. The idempotencyKey retry-replay behavior is consistent with idempotentHint=false, not contradictory.

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?

Dense but front-loaded: the core operation, then constraints, then validation, then the timing/idempotency tips. Every clause carries information, though the two long sentences plus fragments make it heavy to parse.

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 non-idempotent write tool with no output schema and only hint-level annotations, the description covers limits, validation, side effects, timing and idempotency well. It omits failure/error behavior and the shape of the returned status, which keeps it short of a 5.

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 60%, and the description compensates by explaining what records must contain (JSON objects matching the project's schema, 1-500, up to 512 KB) and what wait and idempotencyKey do in practice. slug and sourceDeclaration remain undescribed beyond the schema, so it is not fully compensating.

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 ('Append a batch of records to a dataset') plus the resulting effect ('merged into a new immutable version'). This is clearly distinguishable from read-only siblings like read_dataset and query_dataset.

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 a use case ('a way for an agent without a disk to keep state') and points to a bigger-batch alternative (the SDK's push), but never routes the agent among the many sibling write tools such as submit_knowledge or update_dataset. Usage context is implied rather than explicit.

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