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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds genuinely useful non-schema facts: atomic validation across the batch, an error that names the offending row and column, and a $0.001-per-row cost that is only charged when rows are actually added. It stops short of saying what a successful call returns or how partial-batch edge cases (duplicate rows, unknown columns) behave.

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 sentences, each carrying distinct payload: capacity plus row shape, atomicity plus error format, then cost. The cap and format are front-loaded, and nothing is repeated from the title.

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 two-parameter mutation with no output schema and no annotations covering cost or atomicity, the description carries the important load: row shape, batch cap, validation model, error reporting, and pricing. The remaining gap is the success response – whether inserted row IDs or a count come back – which matters when the caller may need to reference the new rows.

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 50% – the table parameter is documented but rows is a bare array of objects. The description compensates well by explaining that each element maps column names to values and giving a worked example. It adds no constraint detail beyond the schema's own maxItems for the 500 cap, and says nothing about required or unknown columns.

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 ("Add up to 500 rows") and immediately defines the row shape with a concrete example, so the operation is unambiguous. It does not, however, distinguish itself from the closely related siblings rows_upsert and rows_update, which an agent must choose between for any given write.

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?

There is no statement of when to use this versus rows_upsert (which presumably matches on a key) or rows_update. The all-or-nothing validation is a behavioral fact, not routing guidance, so the agent is left to infer the append-only semantics from the example alone.

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