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

Annotations already declare readOnlyHint=false and openWorldHint=true, but the description goes further: it warns this is a REAL ACTION rather than a preview, that a real phone number gets assigned, that other settings are untouched, and that explicit user confirmation must precede the call. That is meaningful context beyond the structured fields.

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?

Four short sentences, front-loaded with purpose, then gating condition, then authority, then the safety warning. No filler and the most important operational caveat ('REAL ACTION, not a preview') is capitalized and prominent.

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?

Covers purpose, gating, auth, and confirmation warnings for a mutation tool with no output schema. The only missing piece is what the agent gets back (e.g., which number was assigned) or failure modes if no numbers are available, but the definition is otherwise complete for correct invocation.

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?

There are zero parameters, so there is nothing to disambiguate; per the baseline for a 0-param tool this is a 4. The description doesn't need to explain inputs, though it could note what identifies the receptionist (it appears to be implicit).

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 ('Finish... by assigning one automatically') on a specific resource ('an existing receptionist that has no phone number yet'), and explicitly carves itself out from onboarding_create_receptionist by saying it operates on an existing receptionist without changing settings.

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 gates invocation on 'onboarding_get_status names this step,' adds an 'Owner only' restriction, and mandates user confirmation before calling. This is about as precise as when-to-use guidance gets.

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