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

Annotations already flag write/destructive/non-idempotent, but the description goes well beyond them: discloses balance spend, irreversibility, no automatic retry, the cost formula, character/part counting rules (160/70 per part), compliance obligations (opt-out link, Spam Act, 10DLC), and the specific uncertainty semantics of a timeout or HTTP 5xx. This is exactly the extra context annotations cannot carry.

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 most consequential facts are front-loaded in the first clause (writes real SMS, spends money, irreversible), which is the right ordering for a destructive tool. It is long and dense, and a few regulatory sentences could be compressed, but nearly every sentence carries distinct operational information rather than filler.

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, non-idempotent send with no output schema, the description covers everything the agent needs: rate/cost model, format constraints, sender resolution, compliance preconditions, and what to do when the result is ambiguous. It even compensates for the absent output schema by naming the tool that confirms whether a message actually went out.

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 schema already defines each parameter, setting the baseline at 3. The description adds real meaning on top: the part-count economics behind body length, that omitting `from` routes through a Notifyre shared number, and that add_unsubscribe_link defaults to false and can itself push the text into another billable part.

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?

Opens with a specific verb and resource plus the critical scope fact: it sends REAL SMS, spends the prepaid balance, and cannot be undone or recalled. This clearly separates it from read-only siblings like notifyre_list_sent_sms or notifyre_get_sent_sms without the agent needing to open any 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?

Gives explicit when-to-use rules ('Only send what the user explicitly asked for: confirm the exact text, the recipients and the sender first'), explicit exclusions ('no contacts, no groups, no scheduling'), and routes to named alternatives for cost (notifyre_list_sms_prices), sender selection (notifyre_list_sms_numbers), and retry verification (notifyre_list_sent_sms).

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