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

Goes far beyond the annotations by explaining the soft-delete tombstone behavior, 30-day recoverability, live change feed event (op:delete), and the exact return value. This is critical context since destructiveHint=true alone might imply permanent deletion, but the description clarifies it's recoverable.

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 value: the core action, recovery semantics, and conditional parameter use with return value. Front-loaded with 'Soft-delete' and free of fluff or redundancy.

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 essential aspects: what the tool does, how it behaves (soft vs hard delete), how to undo, how to observe via change feed, how to use optimistic locking, and what to expect as output. With no output schema, this is a complete picture for an agent.

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 the description doesn't need to explain basic parameters like app_id and collection. It adds value by explaining the purpose of if_match ('optimistic-locked delete') and the shape of the response, which are not fully captured in 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 a specific verb+resource: 'Soft-delete a row from a v2 app's collection.' It clearly distinguishes itself from sibling tools like get_row, update_row, and restore_row by explicitly referencing restore_row and list_deleted_rows, making its unique role obvious.

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?

Provides explicit guidance on when to use the tool and related alternatives: it notes the deletion is recoverable via restore_row and points to list_deleted_rows for viewing deleted rows. It also instructs when to use the optional if_match parameter for optimistic locking, offering clear context.

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