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

With no annotations supplied, the description discloses automatic content additions, stop-list, consent, paused-thread and quiet-hour checks, the permitted lead exception, the 30-minute reply exception, email fallback, and expiry behavior. These details expose important side effects and delivery conditions well beyond the structured schema.

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 front-loaded and nearly every sentence provides operationally important information, with no marketing filler. However, it is a dense single paragraph, and the long nested consent parenthetical plus the unexplained phrase "Doing Work" reduce scanability.

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-heavy messaging mutation with five undocumented parameters and no annotations, it covers routing, content modification, consent and timing restrictions, fallback delivery, expiration, and permitted use. The output schema can carry result details, so omissions such as exact error responses do not materially impede correct selection or invocation.

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?

At 0% schema description coverage, the description supplies crucial semantics for to, conversation_id, and expires_in_minutes, including routing and expiration behavior. It does not explicitly map shop_id to shop selection or body to the message content, leaving those required parameters to straightforward but undocumented inference.

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 opening sentence specifies the action, recipient, sender identity, and scope: texting a customer from the shop number about their job. This distinguishes it from calling, thread-reading, consent-management, and other messaging siblings without relying on the tool name alone.

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 explicitly distinguishes replying with conversation_id from starting a conversation with to, recommends expires_in_minutes for time-sensitive texts, and restricts the tool to transactional rather than sales messages. The registration fallback and timing exceptions also clarify what to expect in common invocation contexts.

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