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

Beyond the annotations (non-readonly, non-destructive, non-idempotent), it discloses the resulting state of the artifact (paused by default, fresh alias, plain manual campaign) and a specific failure mode with its code. It does not state whether the source campaign is left untouched or whether cloning consumes a campaign quota.

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 tight sentences ordered by importance: what gets copied, what the result looks like, then the failure case. No filler or repetition.

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 mutation tool with no output schema, it covers inputs, resulting state and error behavior well. The one gap is that it never says what is returned (presumably the new campaign id/object), which an agent needs to chain follow-up calls.

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 100%, so all three parameters are already documented. The description only restates the effect of status=active (overriding the paused default), which adds a little consequence-level meaning but no new syntax or constraints beyond the enum.

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?

"Duplicate a campaign with its whole routing tree, pixels, postbacks, tags and backup domains" names a precise verb (duplicate) and resource (campaign) and enumerates exactly what is carried over, which separates it from create_campaign and create_campaign_from_meta.

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 tells the agent the default outcome (copy starts PAUSED unless status=active) and the blocked condition (422 domain_problem while the source domain is flagged), which is real when-to-use context. It stops short of explicitly naming a sibling alternative for the non-clone path.

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