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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description adds rich behavioral context: the row returns with original data and creator, version is bumped, only owner/agent can restore, specific error codes are listed (restore_expired, restore_conflict), and it explicitly states the return shape as { row }. No contradiction with annotations.

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 four sentences, front-loaded with the core purpose, and packs substantial detail (behavior, authorization, errors, return) without redundancy. Every sentence earns its place.

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?

Despite having no output schema, the description fully explains what the tool does, how to find inputs, what the return looks like, under what conditions it fails, and who can call it. It is complete for a mutation tool with 3 parameters and no output schema.

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 input schema already covers all three parameters with 100% description coverage. The description adds practical semantics by tying the 'key' parameter to list_deleted_rows, which helps the agent select valid values. App_id and collection are straightforward and schema-described, so this is a modest but meaningful addition over the baseline.

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 clearly states the tool restores a soft-deleted row, explicitly connecting it to 'undoing delete_row'. It distinguishes itself from siblings like list_deleted_rows, delete_row, update_row, and upsert_row by specifying the exact action and resource.

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?

It provides explicit guidance on when to use: 'Find restorable keys with list_deleted_rows' tells users how to locate valid inputs, and 'Owner or agent only' states an authorization prerequisite. It also covers when the tool will not work via failure conditions like restore_expired and restore_conflict.

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