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

Despite annotations like destructiveHint=true, the description clarifies this is a soft delete (tombstoned, recoverable), which is critical behavioral context. It also discloses change feed semantics (op:delete) and the return value, going beyond what annotations alone provide.

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?

The description is three concise sentences that front-load the primary action and then add recovery, feed, and locking details. Every sentence provides essential information with no filler.

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?

The description covers the tool's purpose, recovery window, related tools, change feed visibility, optimistic locking, and return value. Despite no output schema, the return value is stated, making the description complete for this simple delete operation.

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?

The schema already describes all four parameters thoroughly (100% coverage), so the baseline is 3. The description adds meaningful context for if_match as an 'optimistic-locked delete' and implicitly ties key to the row being deleted, adding value beyond the schema.

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 description opens with 'Soft-delete a row from a v2 app's collection,' which clearly identifies the verb (soft-delete), resource (row), and scope. It distinguishes from sibling tools like restore_row and list_deleted_rows by explaining recoverability.

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?

The description gives explicit recovery context: 'restore_row brings it back for 30 days (see list_deleted_rows)' and advises when to use if_match for optimistic locking. However, it stops short of explicitly stating when not to use the tool or comparing with all possible alternatives.

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