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

Annotations declare destructive/open-world/non-idempotent, and the description adds materially: message is delivered immediately, consumes the account's messaging credits, cannot be recalled, and returns the new message id. These consequences (cost, irreversibility, return value) are not derivable from the annotation flags alone.

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?

Front-loads the severity marker 'WRITE, IRREVERSIBLE', then packs constraints, addressing rules, and return value into a few dense sentences with no filler. Length is proportionate to a destructive send operation.

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?

No output schema exists, yet the description states the return value (new message id). Combined with the schema covering all four parameters, an agent has everything needed to call this destructive tool 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 a genuinely non-schema constraint: exactly one of conversation_id or mobile must be supplied (the schema expresses no oneOf), plus E.164 guidance with the US country-code default. The platform/mobile interaction is left unaddressed, keeping it below a 5.

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 a real text message to a customer from the account's number — and distinguishes it from sibling read tools like superphone_get_message and superphone_list_conversations by framing it as a write/dispatch action. The GraphQL mutation name `sendMessage` anchors it further.

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?

Explicit when-to-use and when-not: only send what the user explicitly asked for, to the number they named, and never to opted-out contacts. It also gives the routing rule for the two addressing modes — exactly one of conversation_id (existing thread) or mobile (new recipient).

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