crm_outbound_messaging

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

Annotations already flag side effects (`readOnlyHint: false`, `destructiveHint: true`), but the description only says 'Draft' and never clarifies whether the tool sends the message, queues it, or returns a draft. Given the destructive hint, the absence of send/commit detail is a meaningful transparency gap.

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?

One purpose sentence plus a compact Args list with no filler or repetition. The structure is clear and front-loaded, though the Args section could have been slightly tighter.

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?

An output schema exists, so return-value details are not required. However, the unclear send-vs-draft behavior and missing prerequisites/routing guidance leave an incomplete picture for a side-effecting tool.

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 description coverage is 0%, and the description compensates by defining all five parameters. It supplies otherwise-missing allowed values for channel, intent, and tone, and clarifies that 'message' is a free-text objective rather than the final message 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?

The opening sentence names a specific verb and resource: 'Draft a personalised outbound message to a prospect' and enumerates channels and intents. The personalisation criteria (ICP, value props, role, recent activity) clearly distinguish this from generic email-writing siblings.

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 implies the outbound-messaging use case through examples like cold email, LinkedIn, and follow-up, but it never states when to choose this over sibling tools such as business_write_email or gmail_send_email. No exclusions or alternative-selection guidance is given.

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