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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that disconnect 'wipes stored creds', that unverified-domain sends silently fail recipient rows with no warning, and that enable_tracking provisions a webhook. It also explains the credential hazard behind not exposing connect. These are exactly the behavioral facts an agent needs.

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 description is long but densely packed with operational facts and warnings, with no filler. It front-loads the tool's purpose and then systematically covers each action. A bulleted structure might aid scannability, but the content earns its length.

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 multi-action integration manager with no output schema and no annotations, the description covers the main actions and their side effects well. It omits return details for test_send and doesn't tie the optional email fields to the test_send action, which is a minor but real completeness gap. Overall, an agent can safely invoke the main actions.

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 only 20%, so the description must compensate. It explains the meaning of every action enum value and notes that test_send is a one-shot email. However, html, text, and subject are not described in either the schema or the description, and 'to' is only described in the schema. The compensation is partial, leaving gaps for constructing test_send calls.

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 resource ('BYO Resend integration') and domain ('email campaigns'), then enumerates each action's precise purpose. It also explicitly states what the tool is NOT ('connect' is NOT exposed), which removes ambiguity. This clearly distinguishes the tool and its actions without needing the 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 gives a direct operational rule: call action='domains' before setting a campaign's from_email or reply_to. It also explicitly excludes 'connect' and directs users to the UI, which is valuable guidance. It doesn't explicitly compare against sibling tools like email_send or sending_settings, but the integration-management context is clear enough.

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