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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description adds real value by disclosing the pause-then-archive sequence, that remaining sends stop, that unsent drafts are discarded unless retained, and that the action is reversible. The final sentence about repeated calls only restates idempotentHint, adding no new information.

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?

Four short sentences, front-loaded with the primary action and its consequences in a logical order. The closing idempotency sentence is largely redundant with the annotation, which is the only real 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 destructive, reversible mutation with nested parameters and no output schema, the description covers the important consequences: sends stop, drafts may be lost, restoration is possible, and the call is idempotent. What remains missing is any explanation of 'after_message_id' and of the default value governing draft retention.

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 are two parameters, one of which ('after_message_id', a UUID) is never mentioned in the description at all. The clause about unsent drafts being discarded unless kept loosely gestures at 'discard_unsent_drafts' but never names it or states the default, so most of the parameter surface remains undocumented.

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 ('Pauses an active campaign and archives it') plus the immediate effect ('stopping its remaining sends'). It also implicitly separates itself from discardCampaign by noting 'The campaign can be restored later', though it never names a sibling explicitly.

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?

Usage is implied by 'an active campaign' and by the reversibility note, which hints at when to prefer this over a permanent discard. However, there is no explicit statement of when to use this versus pauseCampaign, discardCampaign, or restoreCampaign, and no preconditions are given.

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