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

Annotations already declare openWorldHint=true and readOnlyHint=false, but the description adds critical context beyond them: the message reaches a real person, cannot be unsent, and requires a preview-then-confirm gate. It doesn't describe rate limits or return format, but the safety profile is well surfaced.

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?

Three front-loaded sentences with zero waste: scope first, then consequence, then the required workflow. Every sentence earns its place.

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 non-idempotent, externally-reaching mutation tool with no output schema, the description covers recipient scope, irreversibility, and the confirm workflow an agent needs to invoke it safely. Nothing essential to correct invocation 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 67% and the schema already documents the confirm preview semantics, message body, subject-for-Email, and contact_id sourcing, so the description largely reinforces rather than extends it. It adds no syntax or format detail for the undocumented location_id. Baseline 3 is appropriate when the schema carries most parameter meaning.

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 (Send) and resource (ONE email or SMS to ONE existing HighLevel contact), and distinguishes itself from the no-bulk pattern. An agent can tell this apart from siblings like highlevel_read_conversation or highlevel_add_note immediately.

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 an explicit two-step workflow: call WITHOUT confirm to preview, show the human, then call again with confirm:true once agreed. It also states the scope constraint ('no bulk send; message one contact at a time'). This is close to a complete usage contract.

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