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

Annotations already declare the safe read-only, non-destructive profile, but the description adds real operational context beyond them: the 30-day restore window, newest-deletion-first ordering, default page size of 50, and that soft-deleted screens are included. The closing 'Read-only' merely repeats the annotation, and it does not cover auth or pagination mechanics beyond the default, so it stops 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?

The purpose and scope are front-loaded, then paging, filtering, restore routing, and the screen inclusion note follow logically. Every sentence serves a purpose except the redundant 'Read-only,' which duplicates the annotation.

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 an output schema present, return values need not be described, and safety is covered by annotations. The description supplies the remaining essentials: scope, retention window, ordering, paging, filtering, and the sibling handoff for restoration.

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 description coverage is 100%, so the schema fully documents q, kind, limit, and offset; baseline is 3. The description explains the intent of filtering ('to find one item') but adds no parameter syntax, format, or constraints beyond what the schema already provides.

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?

States a specific verb and resource ('List soft-deleted items') and scopes it to every content kind within the 30-day restore window. It distinguishes itself from the sibling restore_recycle_bin_item by naming it explicitly and explaining the handoff. An agent can identify the operation and its boundary without opening either schema.

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?

Directly routes the agent: use this tool to list and filter, and pass a row's kind and id to restore_recycle_bin_item for undo requests. It also states how to find a single item via the kind or name filters. The when-to-use and the alternative are both explicit.

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