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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds the key behavioral fact that this dispatch sends an external WhatsApp code to the phone — a real side effect an agent must know about. It also corroborates the non-idempotent nature (each call triggers a new code), though it says nothing about rate limits or failure 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?

Two sentences, front-loaded with the action and its mechanism, no filler. The second sentence is slightly ambiguous in its referent ('il passo successivo' names no tool), which costs a point, but the size is appropriate.

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?

There is no output schema, so the description should orient the agent on what comes back and what to do next. It hints at a successor step but never names complete_registration, and it does not say what state or token the call yields, leaving the two-step flow implicit.

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%, including a formatted WhatsApp example for 'phone', so the schema carries the parameter documentation. The description adds a mild semantic nuance — that name and number together determine existing-user detection — but no format or validation details beyond the schema. 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?

The description states a specific verb+resource ('Registra la persona al sito della farmacia') and explains the concrete mechanism (invio di un codice WhatsApp). It distinguishes itself from the start_login flow indirectly by noting the already-registered case, but it never names start_login or complete_registration, so differentiation relies on inference.

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?

Usage is implied: this is the entry point for a new registration, and the description notes that an already-registered number/name will be handled by the following step. However, no explicit alternative ('use start_login if the user already has an account') or precondition is stated, leaving the agent to infer routing from siblings alone.

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