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

Annotations declare readOnlyHint=false and idempotentHint=false, but the description goes well beyond them: it explains that the campaign is created or topped up and marked ready, that nothing is sent until the user approves on the campaign page, and that review_url must be shown to the user. This is rich behavioral context the annotations cannot convey.

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 action and the safety guarantee, and most sentences carry unique information. However, the no-send guarantee is stated twice ('nothing is sent until they do' and 'Nothing is sent until the user approves it in RankParse'), a minor redundancy in an otherwise dense but earned block of text.

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 non-read-only proposal tool with no output schema, the description covers everything an agent needs: what gets created, the approval flow, the review_url to surface, the site_id/campaign_id relationship, and the approved-status guard. No material gap remains.

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 already 100%, yet the description adds real meaning: contacts must be real researched addresses, one per domain, with personalized subject and plain-text body and no em-dashes; site_id is required only when campaign_id is omitted; and campaign_id must match the campaign's website. This exceeds the schema's plain field descriptions.

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 ('Put outreach emails in front of the user for review') and clearly frames the tool as a proposal gate rather than a send. It implicitly distinguishes itself from siblings like outreach_launch_campaign and outreach_create_campaign by emphasizing user approval, though it doesn't name them directly.

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 branches: pass contacts inline to propose new ones, pass campaign_id without contacts to surface existing copy-ready contacts, use site_id from list_websites, and do not re-propose when status is approved. Conditions that select each path are stated, not inferred.

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