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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety is signaled; the description goes beyond by describing concrete side effects (queued messages pulled back, sent messages remain in threads) that annotations cannot express. It also states irreversibility plainly, which is exactly the context an agent needs before a destructive call.

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 clauses, front-loaded with the action and its side effects, then the irreversibility warning, then the alternative and retry rule. No filler and nothing restated from the schema's structured fields.

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 two-parameter destructive tool with no output schema, the description covers the essentials: what is destroyed, what survives, that it is irreversible, what to use instead for a reversible stop, and how to retry safely. Nothing an agent needs in order to call it correctly is missing.

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 50%: idempotency_key is documented in-schema, and the description reinforces it with retry semantics ("Pass the same idempotency_key when retrying"), which is real added meaning. However, campaign_id is only constrained by format/pattern in the schema and gets no explanation in the description — no statement of where to obtain it or what a valid campaign reference looks like — so the low-coverage gap is only half compensated.

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 ("Deletes a campaign") and immediately distinguishes the operation from the closest sibling behavior by anchoring it to the UI's Delete action and pointing to edit_campaign for the non-destructive path. An agent can tell this apart from edit_campaign, create_campaign, or send_campaign_messages without inspecting schemas.

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?

Gives an explicit alternative and the condition that selects it: "to stop it for now, edit_campaign with status paused." It also tells the agent what to do on retry (same idempotency_key), so both the when-to-use and the when-not-to-use paths are covered rather than inferred.

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