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

Annotations cover the safety profile (destructiveHint=true, openWorldHint=true, non-idempotent). The description adds value beyond that: disconnect 'wipes credentials,' enable_tracking installs a webhook, test_send sends a real email, and the confirmation warning for destructive actions. A genuine addition over the annotations.

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?

Tight and front-loaded: the identity sentence leads, actions are enumerated compactly, then safety/confirmation notes. Every clause carries non-redundant information; no filler.

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?

Covers the multi-action tool well: which action does what, destructive-action confirmation, and the app-only connection constraint. Without an output schema, it should describe return shape for status/domains/test_send, which it does not, leaving a minor gap.

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 partially compensate. It names 'to' for test_send and the from_email concept, and clarifies that action selects among five named behaviors, but html, text, and subject are undocumented anywhere. Baseline 3 with a partial gap remaining.

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 what the tool is (BYO Resend connection management) and enumerates all five actions with parenthetical detail (enable_tracking installs webhooks, domains shows verification state). This clearly distinguishes it from siblings like email_send or sending_settings, but the top-level purpose is framed as a noun phrase rather than a single verb+resource.

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?

Provides explicit procedural guidance: check domains before choosing from_email, confirm disconnect and the test_send address first, and connecting happens only in-app never by pasting a key. Strong when/why context. No explicit exclusions against, e.g., email_send for sending actual campaign mail, so it falls short of 5.

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