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

Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) already flag this as a non-read, non-idempotent operation, but the description adds real substance: nothing is sent until the user approves in RankParse, a draft campaign is created/top-up, and the agent should surface review_url. Minor deduction because 'nothing is sent until they approve it' is stated twice, once in the middle and once near the end.

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 purpose and mostly information-dense, but it is bloated by redundancy: 'nothing is sent until they approve it in RankParse' appears twice, and the site_id/campaign_id rule is restated. Several clauses could be merged without losing meaning.

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 5-param, no-required-param, no-output-schema mutation tool, the description covers conditional requirements, workflow, and the approval gate. It even mentions review_url (the return handle) even though no output schema exists, which is a useful addition, though it does not say what else the response contains.

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 constraints not present in the schema: max 100 contacts enforced alongside 'one per domain', researched real addresses, personalized subject, plain-text body, and no em-dashes. It also explains the site_id/campaign_id linkage rule, which enriches those fields beyond their schema text.

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+resource ('Ask the user to approve outreach emails') and immediately distinguishes itself from the sibling write tools: RankParse creates/tops up the draft campaign and puts emails in the inbox for review rather than sending. An agent can tell this apart from outreach_create_campaign or outreach_add_contacts 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 explicit conditional routing: pass contacts inline when creating, pass campaign_id without contacts to propose a campaign's existing copy-ready contacts, use site_id from list_websites (required when creating; must match when campaign_id is present), and do not re-propose campaigns already approved. This covers when, when-not, and prerequisites.

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