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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: the full state machine (declined, expired, awaiting payment with link, finding expert, booked with next visit, done/cancelled) and a data boundary ('Never includes the customer's details'). It does not cover error behavior for a bad reference.

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?

The purpose is front-loaded, the state list is dense but each item is meaningful, and the closing constraints are terse. No sentence is wasted.

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?

With no output schema, the description usefully enumerates the possible status values, which is exactly what an agent needs. It stops short of describing invalid/expired-reference error handling, but is otherwise complete for a single-param read tool.

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 single parameter is already documented in the schema (hmr_ prefix, returned by request_booking). The description echoes the source of the reference but adds no format or validation detail beyond the schema, so baseline 3 is correct.

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 ('Where a request_booking request stands') and enumerates the concrete states it can return. It is clearly distinguished from the sibling request_booking, which creates the request this tool inspects.

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 ties itself explicitly to a request_booking request and redirects changes to 'the customer messages Helen on WhatsApp', which tells the agent this is read-only and where to route mutations. It lacks an explicit 'use after request_booking' trigger, but the context is clear.

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