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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful context beyond that: 1-2 minute runtime, persistence as a campaign_drafts row, the returned draftId, and common failure modes (expired OAuth, unreachable landing page, over-aggressive CPA filter). It doesn't say whether re-running overwrites prior drafts. Good added value, but not rich enough to warrant a 5 given the annotations already carry the mutation profile.

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?

Front-loaded with the verb and scope, then the sequence, then runtime/failure notes — a sensible ordering. It is somewhat long, and the INTENDED SEQUENCE partially duplicates information already in the sibling tools' domains, but each sentence contributes actionable guidance rather than 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 multi-step, long-running generative tool with no output schema, the description covers what it produces (draftId), where it persists, expected latency, failure modes, and the approval workflow that must precede it. Nothing an agent needs to invoke it correctly is missing.

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 100%, so every parameter including the subtle ones (country granularity, positiveKeywords seeds, campaignGoal flow) is already documented in the schema. The description adds the CPC > targetCpa × 0.5 filter rule, but this same rule is also present in the targetCpa schema description. Baseline 3 is correct when the schema does the heavy lifting.

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 ('generate ... campaign draft') and enumerates the pipeline steps (keyword research, budget/CPA filter, ad-group splitting, AI ad copy). It explicitly distinguishes itself from the sibling publish_campaign_to_google_ads by noting nothing is pushed to Google Ads. An agent can tell exactly what this does and where it stops.

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 INTENDED SEQUENCE gives explicit step-by-step when-to-use: call propose_campaign_goal first, get approval, then call this, then only publish on explicit confirmation. It names the alternative publish tool and the condition (explicit user consent) required to move to it. 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.