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

Annotations already flag this as a non-readonly, non-idempotent, destructive mutation, but the description goes further by scoping that risk: nothing is sent until start_campaign, so creating is safe from a sending standpoint. It also discloses defaults beyond the annotations, notably that the campaign sends from ALL connected mailboxes unless `accounts` plus settings.useAllAccounts = false are used. It does not cover side effects like whether a duplicate name is rejected or what permissions are needed.

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?

The most important fact (draft, does not send) is front-loaded in the first clause, followed by optional payload areas, then the sending-source default, then the lifecycle pointer. Four sentences with no filler, though the second sentence packs a lot of list-like material.

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 7-parameter, deeply nested creation tool the description covers lifecycle (draft to start_campaign), mailbox selection defaults, lead ingestion and A/B step limits. The main gap is that there is no output schema and the description never says what comes back (presumably a campaign id) or what state the created campaign has, which an agent needs for the follow-up start_campaign call.

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 86% schema description coverage, the schema already documents nearly every parameter, including the accounts/useAllAccounts interaction and the variants logic. The description restates the 1000-lead cap, the 5-variant A/B limit and the mailbox default rather than adding new semantics. Baseline 3 is appropriate because the schema is doing the explanatory work.

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?

The description opens with a specific verb+resource+state: 'Create a campaign as a DRAFT — it does not send.' That single clause separates it from update_campaign, start_campaign and create_subsequence without the agent needing to open 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?

It routes the agent to explicit alternatives: use add_leads for full lead details, start_campaign to actually launch, send_test_email to preview a step. It also states the condition for `accounts` (settings.useAllAccounts = false). It stops short of an explicit 'use update_campaign instead when the campaign already exists' exclusion, which is the one realistic confusion.

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