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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description meaningfully adds that credits are spent, that a sent broadcast cannot be undone, and that a scheduled one can be stopped with dialmycalls_cancel_text. However, it does not describe the returned preview/send result or per-recipient failure behavior, so it adds useful but not rich context beyond the annotations.

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?

Two tight sentences with the highest-stakes warning (spends credits, irreversible) front-loaded, followed by prerequisites and the approval/preview flow. No 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, credit-spending broadcast tool with no output schema, the description covers cost, irreversibility, the cancel path, the keyword prerequisite, the message cap, and the confirm=false preview return. Nothing an agent needs in order to call it safely is missing.

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 every parameter (including confirm's preview semantics, send_at's timezone requirement, and message limits) is already fully documented in the schema. The description only restates the confirm=false preview and the 10-message cap, adding no syntax or constraint details the schema lacks.

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 (or schedule) a TEXT MESSAGE (SMS) broadcast') and disambiguates from the sibling send_call by naming the medium explicitly. The scope (real recipients, per-broadcast message count) is clear 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 names prerequisites (active keyword via dialmycalls_list_keywords), the alternative for stopping a scheduled send (dialmycalls_cancel_text), and the approval workflow before sending. The confirm=false preview path tells the agent exactly how to run a dry run first.

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