It is shown that the capacity of the channel modeled by (a discretized version of) the stochastic nonlinear Schrödinger (NLS) equation is upper-bounded by $\log(1+\text{SNR})$ with $\text{SNR}=\mathcal P_0/σ^2(z)$, where $\mathcal P_0$ is the average input signal power and $σ^2(z)$ is the total noise power up to distance $z$. The result is a consequence of the fact that the deterministic NLS equation is a Hamiltonian energy-preserving dynamical system.