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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent). The description adds meaningful behavioral context beyond that: both artifacts 'stay drafts for review' (so nothing is sent), and AI must be configured first. Return format is not covered, but the key behavioral facts are.

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, front-loaded with the core action, then draft status, then prerequisite. No wasted words.

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?

No output schema exists, and the description covers the essential behaviors (AI-generated, draft-only, trigger-delayed, AI prerequisite). It does not address ctaUrl or productId, but for a 5-param tool with 80% schema coverage this is close to complete.

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 80%, so the schema carries most parameter meaning and baseline would be 3. The description adds the timing semantics ('sends it a while after a trigger'), reinforcing the delayMinutes/trigger relationship and the brief's role, going slightly beyond the structured fields.

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 specific verbs (write, build) and resources (follow-up email, draft journey) with the AI-generation angle made explicit. This clearly distinguishes it from create_journey, create_journey_from_recipe, and draft_reply_with_ai without opening their schemas.

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?

Provides a prerequisite ('Needs the AI set up in Settings → AI'), which is useful context, but never states when to pick this over the sibling manual/recipe builders. Usage is implied rather than contrasted with alternatives.

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