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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes far beyond by explaining that the call is proposed rather than performed, returns status='confirmation_required' with action_id and plan_token, and that the draft merely waits in the cabinet for owner test/approval. It also discloses a side effect the schema cannot: the unsubscribe footer is appended automatically.

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 core caveat and then the input contract, which is the right order. The proposal/never-sent point is restated three times ('NOTHING is sent', 'Never claim a campaign was sent', 'PROPOSED, never performed directly'), which is emphatic but slightly redundant.

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 mutating, confirmation-gated tool with no output schema, the description supplies everything needed: required vs optional inputs, format rules, the confirmation handshake and its return shape, and the downstream lifecycle of the draft. Nothing an agent needs in order to call 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?

With 0% schema description coverage, the description carries the full burden and does so: segment is an id or name from email_marketing_campaigns, template is an id or name, and body is plain text with paragraphs separated by a blank line. It also encodes the template-XOR-subject/body constraint that the schema does not express via anyOf. Only the maxLength limits are left to the schema.

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 ('PREPARE a DRAFT e-mail campaign') and immediately scopes it as provisional, which separates it from email_marketing_campaigns (browsing segments) and confirm_action (executing the write). An agent can pick this tool without opening any other definition.

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?

Explicitly enumerates required inputs (name, segment sourced from email_marketing_campaigns) and the mutually exclusive path: EITHER an existing template OR subject+body. It also names the follow-up step (confirm_action) and states the when-not condition — never claim sending or scheduling.

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