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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description earns credit beyond that by disclosing skip semantics for unreadable/absent ids and the exact CONFLICT trigger for stale revisions, which are not in the annotations. It omits the biggest remaining question for a destructive tool: whether rows are recoverable (trash_restore exists as a sibling) or permanently gone.

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 tightly packed sentences with the limit and single-table rule front-loaded, no filler. Slightly telegraphic phrasing ('Workspace tables need why') costs a bit of readability but not much space.

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?

Output schema is present so return values need no explanation, and the description covers the batch limit, single-table rule, missing-id skipping, workspace `why` prerequisite and revision conflicts. The notable gap is recoverability/permanence and any partial-success semantics for a destructive batch delete.

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 all three parameters are already documented in structured form. The description summarizes rowIds, why and expectedRevisions but adds little syntax or meaning the schema does not already carry, so the baseline 3 applies.

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?

Specific verb (delete) plus resource (rows) plus a hard scope constraint: up to 1000 ids, all belonging to one table, with two-table input declared invalid. An agent can immediately separate this from table_append_rows and table_update_row without opening any 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 real preconditions – workspace tables require `why`, and `expectedRevisions` is optional with described conflict behavior – but never routes the agent between alternatives, e.g. when to prefer a single-row update, or whether a deleted row can be brought back with trash_restore. Usage is implied by the constraints rather than stated as when/when-not.

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