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

Annotations already flag destructiveHint=true and non-idempotent mutation; the description adds the substantive 'why' — activate=true starts emailing enrolled contacts, mark_complete flips is_draft false only if validation passes, and the user sees the exact emails during approval. It does not mention retry/duplicate-creation risk or permission requirements, keeping it below a full 5.

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 capability, then operational rules and confirmations in descending priority; no filler sentences. Slightly dense and mixes several concerns (input collection, branching rule, activation safety, sibling preference) in one paragraph without visual separation.

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 17-parameter, side-effecting tool with no output schema, the description covers the core workflow, the emails-vs-nodes decision, and the activation hazard. It omits the failure path (what happens if validation fails so mark_complete is skipped) and the return value/campaign identifier, which an agent would need without an output schema.

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 100%, so the baseline is 3, but the description adds real decision guidance beyond the schema: emails are an ordered sequence shown to the user at approval, while nodes/edges are reserved for branching sequences the user requested. It does not add much on days/hours/tracking/risk-level interplay.

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?

Opens with a specific verb and resource ('Create a ready-to-use outbound email campaign') and then enumerates the concrete side effects performed in one flow (emails, sender profiles, contact import, mark complete, optional activation). It also explicitly differentiates itself from the sibling route: 'Prefer this over create_campaign plus separate steps.'

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 explicit when-to-use ('Use nodes and edges only for a branching (complex) sequence the user asked for'), the alternative it replaces, required user inputs to collect ('Ask for team, name, the email copy and sender profiles if not provided'), and a gating confirmation before the irreversible action ('confirm that with the user first').

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