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

Annotations only declare the basic non-read-only/non-destructive/non-idempotent profile; the description adds substantial behavioral detail beyond them: the copy must pass the same validation enrolment runs (no links, bare domains, stock phrases, unknown tokens, or empty offer) or nothing is created, and it explicitly states DRAFT ONLY with nothing enrolled or sent. This is meaningful, non-obvious behavior disclosure.

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-loads the core action, then layers validation, tokens, and the draft/launch boundary in information-dense sentences with little waste. It is slightly long and packs several distinct topics, but each sentence carries actionable content.

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 an 11-parameter write tool with no output schema, the description covers the critical unknowns: draft-only semantics, validation gating, personalisation tokens, and the launch transition. It defers scheduling detail to the 91%-covered schema, which is reasonable, leaving only minor gaps.

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 91%, so the schema already documents nearly every parameter, making 3 the baseline. The description adds semantic value on tokens ({{greeting}}, {{opener}}, {{offer_pitch}}, etc.) and on the default-sequence-vs-steps behavior, but it does not explain the scheduling parameters (days, hour_from/hour_to, timezone, daily_limit, followup_gaps_days) beyond what the schema provides.

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: 'Create a DRAFT campaign for sites from list_websites (one project)'. It scopes the resource (website campaigns, single project) and distinguishes itself from the generic draft creator by tying inputs to list_websites, so an agent can tell it apart from create_campaign_draft 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 clear context: use list_websites for site_ids, get_campaign and preview_campaign_step to inspect/render templates, and launch_campaign to actually start sending. It also clarifies the draft-vs-launch boundary. It does not explicitly contrast against the sibling create_campaign_draft, so it stops short of full alternative routing.

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