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

Annotations already establish readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered and the description adds real context beyond it: the admin-only restriction, the implicit retention window ('can still be restored'), and the shape of the returned row preview. It does not mention pagination limits beyond the schema, which keeps it short of a 5.

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?

A single dense sentence that front-loads the resource, the recovery constraint, and the access level, then lists return fields. No wasted words and nothing buried.

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?

With no output schema, the description usefully enumerates the return fields (table, id, when/by whom, preview), and the admin note covers the main authorization concern for a 2-param read-only list. The one gap is that the optional 'table' filter parameter is never explained, leaving the agent unsure whether it can scope the listing.

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 50%: 'limit' is fully documented in the schema (max 100, default 25), but the 'table' parameter has no description anywhere. The description only mentions 'table' as a returned field, not as a filter, so it does not compensate for the documented gap in parameter semantics.

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?

Names a specific resource (recently deleted, still-restorable records) and enumerates the fields returned (table, id, timestamp, actor, row preview), so the agent knows exactly what this lists. It does not need sibling differentiation since no other tool in the sibling list covers deleted-record recovery, but it also doesn't explicitly name a neighboring alternative.

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 phrase 'that can still be restored' implies the use case (recovery of soft-deleted rows) and '(admins)' signals a permission gate, which is useful implied guidance. However, there is no explicit when-to-use/when-not, no statement of what to do for already-purged records, and no named alternative (e.g. restore vs. record_history).

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