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

Annotations only declare destructiveHint=true; the description goes further by naming the mutation target (external EHR/PMS) and the optional patient notification side effect, which an agent needs to know before invoking. It stops short of auth requirements, idempotency/double-booking behavior, or error modes.

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 short sentences with the mutation warning front-loaded immediately after the verb, then the parameter constraint, then the endpoint. Zero 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 10-parameter mutation tool with no output schema, it covers the essential operation, side effect and the key parameter constraint. The gap is the absence of any prerequisite or failure context (e.g. valid patient_id, slot conflicts), but the core is complete.

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 description coverage is 100%, so the baseline is 3. The either/or note on end_time vs appointment_type_id is already present in the schema descriptions, making the description's parameter guidance largely redundant rather than additive.

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 ('BOOK a new appointment') and explicitly identifies the side effect ('creates an appointment in the connected EHR/PMS'). It is cleanly distinguishable from siblings like nexhealth_create_patient and nexhealth_update_appointment.

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 gives one real invocation rule ('Provide either end_time or appointment_type_id'), which is genuine when-to-pass guidance. However, it offers no context on when to book versus checking nexhealth_list_appointment_slots first, nor any prerequisite conditions (patient/provider/location must already exist).

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