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

Beyond the destructiveHint/openWorldHint annotations, the description discloses real behavioral traits: it wipes every item record, targets the LIVE channel, pauses the integration during the run, and debounces repeats within 5 minutes so no new run starts. That cooldown and pause behavior is exactly the kind of operational detail annotations cannot express. It does not describe whether an in-flight run can be cancelled or what partial-failure state looks like, so it is strong but not exhaustive.

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?

Two sentences, front-loaded with the destructive scope and followed by the usage trigger and confirmation gate; there is no filler. The first sentence is clause-dense (scope, side effect, cooldown) but parses cleanly in reading order.

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 destructive, open-world bulk operation with no output schema, the description covers the essentials: what is destroyed, which channel is affected, the integration pause, the repeat cooldown, and the confirm gate. The unaddressed project_id and the absence of failure-mode detail leave a small gap, but an agent could call this correctly from the definition as written.

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 67%; ad_id and confirm are already documented in the schema, and the description's confirm guidance largely restates the schema text. The one undocumented parameter, project_id, is never explained in the description, so it does not compensate for the coverage gap. Baseline 3 is appropriate.

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 verb pair (clean + resubmit) and an explicit scope ("AD-wide ... all — clear every item record and submit all again to the LIVE ad channel"), which is concrete enough to distinguish it from narrowly scoped siblings such as clean_resubmit_ad_items or clean_ad_items. It never names an alternative sibling explicitly, so the agent must infer the scope contrast from the word "all".

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?

"Use this when the user asks to rebuild all listings" gives a clear selection context, and the description adds a hard precondition ("Needs confirm:true after the user agrees") that gates invocation. It stops short of naming when-not-to-use or pointing to the non-"all" siblings for partial rebuilds.

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