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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds the one behavioral fact annotations cannot express: a hard precondition on campaign state and the reason (the ledger reflects what was actually sent). It does not say whether unsent fields are merged or replaced, or what error surfaces when the precondition fails.

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 action and followed by the constraint. The second sentence is longer than strictly necessary in its rationale, but it justifies a restriction the agent would otherwise discover only through an error.

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 six-parameter mutation with 17% schema coverage and no output schema, the description covers neither which fields are editable nor what the call returns or how it fails. An agent knows it may change a draft but not what it can change or what happens to fields it omits.

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 17% — only the 'project' parameter is documented in the schema — and the description names none of the six parameters. Editable fields (name, subject, body, recipientScope) and the meaning of campaignId are left entirely unstated, so the description does not compensate for the coverage gap.

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?

"Change a draft campaign" supplies a specific verb (change) and resource (campaign) plus a scoping qualifier (draft) that separates it from draft_campaign and list_campaigns. It stops short of explicitly naming the sibling an agent should reach for when the campaign is not a draft.

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?

The description gives a clear eligibility rule — only draft campaigns can be changed, sent campaigns cannot be edited — which tells the agent the precondition for calling it. It does not name an alternative for the sent case (e.g. duplicate or re-draft), leaving the fallback path to inference.

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