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

Adds real behavior beyond the annotations: partial-update semantics ('Fields you omit keep their value'), the not_a_draft error condition, and the side-effect disclaimer 'Nothing is sent.' Annotations only tell the agent this is a non-idempotent, non-destructive write. The one gap is that the confirm parameter's hard-to-undo guard is never explained in prose, so an agent may not know when that prompt appears.

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: what it edits, the patch semantics, then the exclusion and alternatives. The precondition and routing information is front-loaded and no sentence is filler.

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 10-parameter mutation with no output schema, the description covers the essential decision inputs: draft restriction, partial update behavior, error path, and side-effect absence. Only the confirm-guard interaction and the shape of the success response are unaddressed, which is acceptable given the rich schema descriptions.

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 already 90%, so the baseline is 3; the description adds genuine meaning by grouping the fields and clarifying that this is a patch-style update where omitted fields are preserved. It still says nothing about the confirm flag or the relationship between hour_from/hour_to defaults.

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 (Change) plus resource (a DRAFT campaign's setup) and enumerates the editable surface: name, offer, daily limit, sending days/hours, timezone and follow-up gaps. This distinguishes it cleanly from neighbors like update_campaign_sequence, rename_campaign and update_offer.

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 precondition (DRAFT only), the failure mode for the wrong state (live campaigns refuse with not_a_draft), and names the two alternatives to use instead for live campaigns. Nothing is left to inference.

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