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

Beyond annotations (readOnlyHint, idempotentHint), the description discloses soft-delete behavior, the 30-day retention window, purged rows appearing with purged:true, and that purged rows cannot be restored. It also reveals the return shape, adding significant context.

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?

Multiple sentences, each conveys distinct information: purpose, restore behavior, permissions, purged handling, and output shape. No fluff; front-loaded with the core action.

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?

No output schema exists, so explicitly stating the return object ({ rows, next_before }) is essential. The description also covers auth constraints and edge cases (purged rows), making it complete for a tool of this complexity.

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% with all four parameters described, including limit default and before cursor. The description doesn't add parameter-specific semantics beyond what the schema already provides, 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?

The description opens with a specific verb and resource ('List a collection's recently deleted rows') and names the 'recovery bin.' It also references restore_row and soft-delete semantics, distinguishing it from list_rows and other sibling tools.

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?

Clearly states when this is relevant: 'Deleting a row is a soft delete, so it can be restored with restore_row until recoverable_until passes.' It also notes permission requirements (owner/agent only) and independence from read permissions. It doesn't explicitly contrast with list_rows, but the context is clear.

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