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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the bar is lower. The description adds genuinely useful context that the call charges the prepaid balance and requires user confirmation, plus the foreign-rate prerequisite. However it says nothing about scheduling (send_at / send_window / expires_at), the idempotency behavior on retry, or what happens to partially failed batch sends — meaningful omissions for a 500-recipient paid mutation.

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?

Four short sentences, front-loaded with the core action, recipient shapes and cost implication, then the confirmation gate. The telegraphic fragments ('Requires purpose.') are efficient rather than wasteful, though a slightly more structured ordering could improve scanning.

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?

With annotations, a full output schema and 100% parameter documentation, the description's job is mainly to convey cost, risk and confirmation. It does that well, but for a 12-parameter paid bulk-send tool it omits the scheduling and retry/idempotency story that an agent would want before invoking it.

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 100%, so every parameter already carries its own explanation, setting the baseline at 3. The description adds only the subject+SMIL pairing concept and the 500-recipient cap, both of which the schema already encodes; it says nothing about purpose, template_id vs smil, reference, or idempotency_key semantics beyond what is written in the schema.

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 states a specific verb and resource ('Send an MMS (subject + SMIL body)') and enumerates the three supported recipient shapes with the 500 cap. It implicitly separates itself from send_sms and send_voice by naming the MMS channel, but never explicitly says how it differs from those 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?

It gives concrete pre-call conditions: wait for explicit user confirmation, a purpose is required, and foreign destinations need a quoted country rate first. It stops short of naming an alternative tool (e.g. send_sms for plain text) for cases where an agent picked the wrong channel.

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