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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: results are limited to the retention window, sorted most-recently-deleted first, and exclude downgrade-removed sites that self-restore. It stops short of stating what happens to entries that age out of the window.

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?

Three short sentences, each load-bearing: the scope, the ordering guarantee, and the exclusion rule. Front-loaded with the core purpose and no filler.

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 simple two-parameter read tool with no output schema and annotations covering the safety profile, the description supplies the scope, ordering, and exclusion semantics an agent needs. Only the fate of sites past the retention window is left implicit.

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% – limit and offset are fully documented with defaults, bounds, and clamping behavior in the schema. The description adds no pagination or format detail, so baseline 3 applies.

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+resource (list deleted sites) and immediately qualifies it with the restore-eligibility scope, which distinguishes it from the sibling list_sites and pairs it with restore_site. An agent can tell exactly what set of entities is returned.

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?

Makes clear this is the discovery step for restorable sites and explicitly carves out downgrade-removed sites as out of scope, which prevents a wrong call. It does not, however, explicitly name restore_site as the follow-up tool or state prerequisites, so a 4 rather than a 5.

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