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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description adds real context beyond them: it consumes SMS credit, cannot be undone, and returns a message id per recipient plus the remaining balance. The confirmation requirement and balance-check prerequisite are behavioral facts the annotations cannot express.

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?

Single dense sentence with the destructive/cost warning front-loaded ahead of the mechanics, so nothing important is buried. The all-caps opening clause is effective for a dangerous write but slightly noisy; every clause still carries information.

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 destructive write with no output schema, the description covers cost, irreversibility, recipient limits, phone format, the confirmation gate, the prerequisite balance check, and what the response contains. An agent has everything needed to decide and invoke correctly.

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 100%, so the baseline is 3, but the description adds the international format with a concrete example (+393331234567) and restates the confirm gate in operational terms. It does not document the optional `from` sender parameter or the 1600-character text limit, leaving those to 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?

States a specific verb and resource ("send an SMS to 1-50 phone numbers") plus the endpoint POST /sms/send, which cleanly separates it from siblings like emailchef_send_email and emailchef_send_campaign. The recipient count and format constraint are stated up front, so an agent knows exactly what the call does without opening the schema.

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?

Explicitly routes the agent to a prerequisite sibling ("Check emailchef_get_sms_balance first") and imposes a hard human-in-the-loop gate ("send only with the user's explicit go-ahead (confirm must be true)"). It also flags the cost and irreversibility condition that should drive the decision to call at all.

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