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

Annotations only say non-readOnly, non-idempotent, openWorld. The description adds substantial context beyond that: the message is real and cannot be unsent, a read-back confirmation step is required, consent/DND constraints apply, and there is a 100-message-per-day cap.

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 actor, action and scope, then adds constraints in a single dense paragraph. Slightly long and dash-heavy, but nearly every clause carries operational weight; minor trimming would help.

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 an irreversible mutation with no output schema, the description covers the essentials: preconditions, addressing options, confirmation workflow, consent rules, and rate limits. An agent has enough to invoke it safely.

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% and the schema descriptions already state 'Preferred' for contact_id and 'used only if a new contact has to be created' for name. The description largely repeats this, adding no syntax or format detail beyond the schema, so baseline 3 applies.

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+resource (send one SMS from the agency's GoHighLevel to one contact) with clear scope limits ('one person per call'). It implicitly distinguishes itself from ghl_send_email by channel and routes the agent to ghl_find_contacts for obtaining a contact_id.

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 preconditions ('For an AGENCY with GoHighLevel connected'), two clear addressing modes (contact_id preferred, or phone which creates a contact), and named hard exclusions (never message DND contacts, only consented people).

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