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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: a 30-day retention window and the fact that only restorable items appear. It says nothing about ordering, result limits, or what the returned list looks like.

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 with no filler; the triggering condition comes first. It is arguably too terse to carry the parameter information the schema omits, but as a piece of prose it earns its place without waste.

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?

For a low-complexity, single-optional-param read tool with no output schema, the description covers timing, scope, and the restore-relevant subset, which is close to sufficient. The unaddressed kind filter and the absence of any sense of the returned list's extent leave a real gap for an agent trying to call it correctly.

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 0% and there is one meaningful parameter (kind) that the description never mentions — an agent reading only the description would not know the results can or should be filtered by item type. The enum values are self-explanatory in the schema, but the description does no work to compensate for the coverage gap or to explain behavior when kind is omitted.

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 states a specific verb and resource ('see what they deleted') and scopes it ('last 30 days', 'can still restore'), which reads naturally as a recently-deleted listing. It does not name the sibling it is distinct from (restore_deleted, confirm_delete), but the read-vs-act distinction is inferable from 'see'.

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 opens with 'Use this when the user wants to see what they deleted in the last 30 days and can still restore,' which is an explicit triggering condition and implicitly defines the window in which the tool is meaningful. There is no when-not guidance and no alternative tool named for adjacent intents like restoring or permanently deleting.

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