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

The annotations already flag destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the baseline safety profile is known. The description adds valuable context by emphasizing that the tool 'sends real email to real people', implying irreversibility and human impact, and by stating the confirmation precondition before setting confirmed: true. It does not add unnecessary detail beyond that.

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?

Three short sentences carry all the essential guidance with zero filler. The most important warning ('real email to real people') is front-loaded, followed by the confirmation requirement and the address cap.

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 low-complexity tool with two parameterscheschema and an output schema absent, the description covers the critical invocation conditions: the dangerous side effect, the needed confirmation, and the maximum list size. It only lightly addresses what happens when an address is invalid or whether calling with confirmed: false has any effect, but those gaps are not critical for correct use.

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 50%, with the confirmed parameter already described in the schema. The tool description reinforces the meaning of confirmed ('get an explicit yes before calling with confirmed: true') and refers to emails as an 'address list', but it mostly restates what the schema's maxItems and confirmed parameter description already convey. It adds some clarity but does not substantially compensate for the undocumented emails array.

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 the specific verb-resource pair 'Email referral invitations', which immediately identifies the tool's action and subject. It also makes the real-world, email-sending nature explicit, distinguishing it from nearby sibling tools like split_send_message by tying it specifically to referral invites.

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?

The description gives an explicit workflow: show the creator the exact address list)Skip while you wait? I found in instructions:

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