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

Annotations already declare destructiveHint/idempotentHint, but the description adds non-derivable behavior beyond them: credit use requires confirmed=true and explicit user approval, and writes are never auto-retried. The whole-step-set replacement warning is exactly the kind of side effect an agent cannot infer and would otherwise cause data loss with.

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?

Dense and front-loaded, with the destructive precondition and the alternative endpoint placed first. The opening "Update campaign. Update a draft campaign." is mildly redundant, but the rest of the sentences each carry a distinct constraint.

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, non-idempotent mutation with no output schema and a nested body, the description covers eligibility, confirm gating, retry behavior, and set-replacement hazards. It doesn't say what a successful response looks like, which is the remaining minor gap.

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 only 33%, so the description must compensate and largely does: it encodes the mutual-exclusivity rule for property_ids/contact_ids/list_ids that the schema does not express as a oneOf, and explains steps as replace-all. Secondary body fields (name, description, qr_code_url, address_to, contact fields) get no mention, which keeps it from a 5.

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 the verb and resource ("Update a draft campaign") and immediately narrows scope with "Only draft campaigns can be updated," which is the key distinction from the other campaign tools. An agent can tell this apart from dealmachine_mail_campaign_add_properties or _send without opening a schema.

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 explicit preconditions (draft-only), a field-level rule (audience updates must use exactly one of property_ids, contact_ids, or list_ids), and names the correct alternative endpoint for ready/active/paused campaigns. It also states the approval gate before mutation, so the agent knows when-not and what to do instead.

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