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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description reinforces and extends this with specific behavioral disclosures: 'NO message is sent and NO state changes', the gate re-runs at send time, and the tool never delivers anything. It also adds cost and latency context and clarifies it does not evaluate two-party recording consent. No contradiction with annotations exists.

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 substantial but well-organized with clear sections: core purpose, example user queries, WHEN TO USE, WHEN NOT TO USE, COST, and LATENCY. The most decision-relevant information (preview mode, no state changes, same gate as send_message) is front-loaded. The examples earn their place by showing both a simple SMS case and a follow-up email case.

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 compliance-checking tool with no output schema, the description tells the agent what the result will convey ('whether a send would be permitted ... names the exact rule and how to remediate'), when to use it as a guard, what it will not do, and its cost/latency profile. Given the moderate parameter complexity and the rich sibling context, nothing essential for an agent to invoke it correctly is missing.

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?

Though schema coverage is 100%, the description adds important semantic guidance beyond the schema: recipient_id can be E.164 or email, content must be the real message body for a meaningful preview, channel can be omitted to auto-infer, and country_code drives jurisdiction. The example invocations demonstrate exactly how to populate the parameters for realistic requests, which materially helps an agent call the tool correctly.

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 names a specific verb ('pre-flight'), a specific resource ('the compliance gate'), and a specific behavior (determines whether a send would be permitted without sending). It explicitly distinguishes itself from send_message and call_business by noting it runs the same gate 'in preview mode' with no message sent and no state changes. This is far beyond a generic restatement of the tool name.

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 'WHEN TO USE' section spells out concrete triggering conditions ('anything tagged marketing, any SMS to a US number, any message to an EU/UK or Canadian recipient') and the 'WHEN NOT TO USE' section lists exclusions, including voice recording consent and treating legal=true as a permanent license. It also directs the agent to proceed to send_message if legal=true, giving explicit decision guidance.

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