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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds two meaningful behavioral facts beyond that: access is restricted to admins, and the listed rows are only those still within a restorable window. It does not describe pagination or the effect of omitting the optional table filter.

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 front-loaded sentence that packs the resource, the restore window, the permission gate, and the returned fields without filler. The enumeration of return fields ('table, id, when and by whom, and a preview') could be tightened but is not wasteful.

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 what each row contains and states the admin restriction and recovery window, which is enough for an agent to decide whether to call it. Only pagination behavior and the semantics of the optional table filter remain uncovered.

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 only 50%: 'limit' is documented (max 100, default 25) but 'table' has no schema description. The description mentions 'table' but in the context of returned fields rather than explaining that it filters results or that it is optional, so it only partially compensates for the gap.

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 names a specific resource with a clear qualifier: records that were recently deleted but are still restorable. That scope is distinctive and lets an agent separate it from siblings like record_history or list_record_files, even though the verb ('list') is only implied by the tool name.

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?

Usage is only implied: '(admins)' signals the required privilege and 'can still be restored' hints at a recovery-oriented workflow, but there is no explicit statement of when to call this instead of alternatives, nor any reference to a restore/undelete counterpart.

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